© 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. 9983
    Prev
    Next
    INDEX
    Explanations

    casual to formal explanations

    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
    न
    1.18
    ி
    1.16
    enio
    1.15
    es
    1.04
     noma
    0.97
    lhe
    0.96
     Enth
    0.96
    ean
    0.95
    PointerException
    0.95
    会の
    0.94
    POSITIVE LOGITS
    uerre
    1.28
    ged
    0.98
    ittarius
    0.98
    ُر
    0.96
     więc
    0.94
    铃
    0.93
    tta
    0.93
    ostino
    0.92
    }+{\
    0.90
    ウター
    0.89
    Activations Density 0.052%

    No Known Activations