© 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. 1146
    Prev
    Next
    INDEX
    Explanations

    closing html head tag

    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
    1.40
     an
    1.36
     a
    1.35
     the
    1.31
     and
    1.27
     '
    1.21
     "
    1.17
     people
    1.07
     forms
    1.06
     (
    1.05
    POSITIVE LOGITS
     irmão
    2.14
     mencionar
    2.08
    𒀝
    2.03
     aplicativo
    1.99
    𒈥
    1.98
    𒂆
    1.92
    𒀖
    1.91
    𒌨
    1.91
    ࢮ
    1.91
    𒈪
    1.91
    Activations Density 0.000%

    No Known Activations