© 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-16K
    7. 8894
    Prev
    Next
    INDEX
    Explanations

    HTTP methods and annotations

    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
    ból
    1.20
    et
    1.12
    b
    1.09
    bly
    1.04
    prised
    1.02
    h
    1.01
    Type
    0.95
    am
    0.94
    j
    0.94
    bound
    0.92
    POSITIVE LOGITS
     or
    1.19
    𝓸
    1.12
     herhangi
    1.11
    といった
    1.09
    หรือ
    1.08
    とする
    1.08
     idempotent
    1.04
    起き
    1.03
    𝙾
    1.02
    IST
    1.01
    Activations Density 0.160%

    No Known Activations