© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 31565
    Prev
    Next
    INDEX
    Explanations

    online forums and discussions

    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
    ی
    1.00
    âne
    0.97
    گاه
    0.96
    ból
    0.95
    و
    0.93
    ية
    0.92
    لک
    0.92
    irán
    0.90
    ǎng
    0.87
     baratos
    0.87
    POSITIVE LOGITS
    T
    0.92
    ];
    0.89
     whichever
    0.89
    L
    0.88
    V
    0.86
    N
    0.85
     explore
    0.84
     boron
    0.83
     waypoint
    0.83
    D
    0.82
    Activations Density 0.003%

    No Known Activations