© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5937
    Prev
    Next
    INDEX
    Explanations

    kidnap abduction nap

    np_acts-logits-general · gemini-2.5-flash-lite

    kidnapping

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_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
    秸
    0.46
     निवेश
    0.40
    TAM
    0.40
    لو
    0.40
    Investment
    0.40
     冬
    0.38
    Alder
    0.38
     <%=
    0.38
    ワ
    0.38
    Minor
    0.37
    POSITIVE LOGITS
     kidnap
    0.74
     kidn
    0.72
     kidnapped
    0.72
     kidnapping
    0.70
     abduction
    0.70
     abducted
    0.68
     अपहरण
    0.55
     waking
    0.52
    nap
    0.47
     납
    0.46
    Activations Density 0.000%

    No Known Activations