© 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. 393
    Prev
    Next
    INDEX
    Explanations

    desensitization, retraumatization, survivors

    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
    a
    0.97
    ي
    0.93
    ه
    0.89
    e
    0.83
    на
    0.78
    т
    0.77
    다른
    0.76
    i
    0.76
    에
    0.75
     bem
    0.74
    POSITIVE LOGITS
    ϋ
    1.11
    otone
    1.08
    ánto
    1.07
    addena
    1.06
    axos
    1.04
    <unused1681>
    1.04
    ómago
    1.04
    ınar
    1.04
    inks
    1.03
    argent
    1.02
    Activations Density 1.505%

    No Known Activations