© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 8572
    Prev
    Next
    INDEX
    Explanations

    resource names and attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_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
    ные
    2.19
    ด์
    2.12
    ка
    2.02
    ক্ষ
    1.94
    л
    1.93
    ations
    1.89
    다른
    1.87
    ко
    1.85
    ное
    1.85
    ת
    1.77
    POSITIVE LOGITS
     MODKEY
    2.23
    fileID
    2.08
    /}
    1.97
     }^{\
    1.94
     }^{*}
    1.83
     }_{
    1.81
     ניתן
    1.76
     potro
    1.74
    ীব্র
    1.73
    wb
    1.69
    Activations Density 0.123%

    No Known Activations