© 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. 170207
    Prev
    Next
    INDEX
    Explanations

    search multiple, methamphetamine on, minutes back

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

    material descriptions and components

    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
     S
    0.50
     P
    0.50
     A
    0.50
     I
    0.46
    эм
    0.45
     J
    0.45
     T
    0.42
     F
    0.42
     Traits
    0.42
     B
    0.42
    POSITIVE LOGITS
     обме
    0.50
    utlich
    0.48
     verbo
    0.48
    ichtlich
    0.47
    ahami
    0.47
    änglich
    0.47
    Якщо
    0.47
    ifiziert
    0.46
    blich
    0.45
    קת
    0.45
    Activations Density 0.001%

    No Known Activations