© 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. 13-GEMMASCOPE-2-RES-16K
    7. 825
    Prev
    Next
    INDEX
    Explanations

    are you or are there questions

    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_13_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
    u
    2.85
    м
    2.54
    a
    2.40
    y
    2.31
    e
    2.31
    에
    2.30
    ي
    2.28
    ا
    2.22
    ০
    2.21
    an
    2.14
    POSITIVE LOGITS
    ExpNow
    1.84
    𝐤
    1.76
    Kick
    1.74
    Hiking
    1.73
    ControlType
    1.69
    ෑම
    1.67
     আমর
    1.67
     kicking
    1.66
    Elastic
    1.63
    यॉर्क
    1.63
    Activations Density 1.776%

    No Known Activations