© 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. 7-GEMMASCOPE-2-RES-16K
    7. 55
    Prev
    Next
    INDEX
    Explanations

    State Government apology

    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_7_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
     trai
    1.56
    jak
    1.53
    漑
    1.47
    照
    1.43
    )=\{
    1.40
     sulph
    1.37
    љашње
    1.37
     коли
    1.37
     कॉम्प
    1.33
     套
    1.33
    POSITIVE LOGITS
    endem
    2.14
    equivalent
    1.88
     Multif
    1.82
     Anti
    1.77
     Equivalent
    1.76
     Wake
    1.76
     Felt
    1.76
    बाई
    1.75
    Control
    1.75
     Control
    1.74
    Activations Density 0.000%

    No Known Activations