© 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
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 913
    Prev
    Next
    INDEX
    Explanations

    want me to elaborate another

    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
     Individual
    1.08
     Means
    0.98
     Dan
    0.97
     Aliens
    0.97
     Dispersion
    0.95
     other
    0.95
     ග
    0.93
     Divers
    0.92
     individual
    0.90
     Div
    0.89
    POSITIVE LOGITS
     alterações
    1.39
     дописа
    1.26
    LaTeX
    1.24
     অভিভাব
    1.22
    rotz
    1.22
    funciones
    1.22
    もり
    1.21
    旄
    1.18
     заместитель
    1.18
    áneamente
    1.17
    Activations Density 0.011%

    No Known Activations