© 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-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 32514
    Prev
    Next
    INDEX
    Explanations

    experimental

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_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
    𝐠
    1.28
    𝐨
    1.13
    يع
    1.09
     unquestionably
    1.06
     allemand
    1.06
    джи
    1.05
     módulos
    1.05
     experimentos
    1.04
    𝕨
    1.04
     equipos
    1.03
    POSITIVE LOGITS
    z
    1.19
    os
    1.17
     and
    1.16
     
    1.15
     on
    1.14
    ts
    1.11
    ang
    1.08
    are
    1.05
     to
    1.01
    ai
    1.00
    Activations Density 0.002%

    No Known Activations