© 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. 154143
    Prev
    Next
    INDEX
    Explanations

    simple, careful, money

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

    not provide explicit content

    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
    gladbach
    0.48
     Gough
    0.47
     abandonar
    0.47
     Vestone
    0.47
    𒅁
    0.47
    ിക്കാം
    0.46
     limpar
    0.46
    явить
    0.45
    ilebilir
    0.45
     Veamos
    0.44
    POSITIVE LOGITS
    क्योंकि
    0.53
    _
    0.52
    ah
    0.51
    2
    0.50
    EL
    0.49
    ana
    0.47
    iva
    0.47
    은
    0.46
    ED
    0.45
    NA
    0.45
    Activations Density 0.004%

    No Known Activations