© 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. 13336
    Prev
    Next
    INDEX
    Explanations

    Google DeepMind

    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
    ruzione
    1.00
    arbeiten
    0.96
    kę
    0.95
    UN
    0.94
     Hrvatske
    0.89
    و
    0.86
    ྪ
    0.85
    eses
    0.83
    <{},
    0.83
    ওসি
    0.82
    POSITIVE LOGITS
    です
    1.22
    ㅏ
    1.09
    ती
    1.08
    era
    1.05
     haus
    1.01
    ০০০
    0.99
    }}}\
    0.99
    ینگ
    0.98
     (
    0.97
    으로는
    0.96
    Activations Density 0.064%

    No Known Activations