Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-16K
    4. 9178
    Prev
    Next
    INDEX
    Explanations

    punctuation and numbers

    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_22_width_16k_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
     Wyd
    0.82
     posiada
    0.78
     असून
    0.77
     हमे
    0.75
     Electric
    0.75
     welchem
    0.73
    ॕ
    0.72
     kirj
    0.71
     Automatic
    0.71
    طار
    0.70
    POSITIVE LOGITS
    \%).
    0.91
    ).
    0.91
     \%)$.
    0.88
     例文帳に追加
    0.84
    ]$.
    0.83
     $)$.
    0.83
    ].
    0.82
    "].
    0.81
    例文帳に追加
    0.78
    .”—
    0.77
    Activations Density 0.091%

    No Known Activations