© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-16K
    4. 3692
    Prev
    Next
    INDEX
    Explanations

    acting purely on instinct; seen as: a mental illness; often seen as intensely passionate; the foundation for many streaming architectures; seen as the most secure; described as wise; perceived as lacking clear regulatory oversight; seen as agents of good; seen as harmful; perceived as different; seen as short-sighted.describing roles and qualities after 'as'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ться
    1.19
    ו
    1.13
    SSE
    1.10
    o
    1.09
    RENCE
    1.07
    س
    1.05
    ্কার
    1.04
    crumb
    1.04
    ﻭ
    1.04
     MEMBERS
    1.03
    POSITIVE LOGITS
    '
    1.89
    ä
    1.34
    .
    1.21
     enz
    1.15
     spes
    1.13
    '%
    1.13
    '";
    1.13
     n
    1.13
    '",
    1.12
     ​​
    1.11
    Activations Density 0.131%

    No Known Activations