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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 3452
    Prev
    Next
    INDEX
    Explanations

    building details, access control

    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
    ுங்கள்
    0.86
     노
    0.77
     カ
    0.75
    UCLEAR
    0.74
     テ
    0.73
     شماره
    0.71
    oretically
    0.70
    C
    0.70
     後
    0.69
     শরনার্থ
    0.69
    POSITIVE LOGITS
    te
    0.83
    ato
    0.73
    ige
    0.73
    els
    0.70
     }}{
    0.66
    -.
    0.64
    .\"
    0.64
    ements
    0.64
    atives
    0.64
    anta
    0.64
    Activations Density 0.815%

    No Known Activations