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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 3752
    Prev
    Next
    INDEX
    Explanations

    continuation words

    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
    a
    1.25
     kudu
    1.22
    ல்
    1.19
    нием
    1.19
     suur
    1.18
     للغاية
    1.16
     bruker
    1.14
    場合に
    1.14
    ی
    1.14
    نی
    1.13
    POSITIVE LOGITS
    dır
    1.18
    m
    1.11
    efeller
    1.03
    itimate
    1.03
    ОО
    1.02
    donate
    1.02
    weapp
    1.00
    goài
    1.00
    АЗ
    0.98
    sdk
    0.98
    Activations Density 0.199%

    No Known Activations