© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 136952
    Prev
    Next
    INDEX
    Explanations

    passenger lists, birth records, security data

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

    project setup and continuation

    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_31_width_262k_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
     triple
    0.46
     per
    0.43
     Macbook
    0.39
     temperature
    0.39
     double
    0.39
     منطقه
    0.39
     rhombus
    0.39
    ->
    0.39
     insufficiency
    0.39
    io
    0.38
    POSITIVE LOGITS
     возможности
    0.52
    첼
    0.46
     опубли
    0.46
    நீங்கள்
    0.45
     lehetős
    0.45
    opportunities
    0.45
     ठिकाणी
    0.44
     возможность
    0.44
     возможностей
    0.44
    anfa
    0.43
    Activations Density 0.000%

    No Known Activations