© 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-262K
    4. 3119
    Prev
    Next
    INDEX
    Explanations

    numbers, version, threat, waiting

    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_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
    ف
    1.52
    s
    1.51
    د
    1.32
    affichage
    1.30
    affiche
    1.27
    quettes
    1.27
    nogo
    1.24
    tweets
    1.23
    kult
    1.22
    announce
    1.21
    POSITIVE LOGITS
    ни
    1.45
    いた
    1.18
    ment
    1.16
    たち
    1.10
    生
    1.08
    ut
    1.06
    美元
    1.06
     whose
    1.05
     providing
    1.05
     delivering
    1.04
    Activations Density 0.001%

    No Known Activations