© 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-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 10375
    Prev
    Next
    INDEX
    Explanations

    you, could you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Bundes
    0.93
     corrispond
    0.92
     குறி
    0.85
    উন্ট
    0.85
     pengetahuan
    0.84
    ἥ
    0.83
    ancellationToken
    0.83
     />;
    0.83
     unidad
    0.83
    Raz
    0.83
    POSITIVE LOGITS
    族
    0.81
    lify
    0.80
    族的
    0.80
    lje
    0.79
    amom
    0.76
    lery
    0.74
     (’
    0.74
    essero
    0.73
     gothic
    0.73
    iglio
    0.73
    Activations Density 0.001%

    No Known Activations