© 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. 136635
    Prev
    Next
    INDEX
    Explanations

    typically between

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

    ethical and defensive security

    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
    www
    0.47
    ит
    0.47
     \{
    0.46
     www
    0.45
     context
    0.44
    ..(
    0.44
    ка
    0.44
    ...(
    0.44
     stressful
    0.43
    Inde
    0.43
    POSITIVE LOGITS
    enamefont
    0.53
     użyt
    0.51
    ⵕ
    0.51
    produkte
    0.51
     vitesses
    0.51
     Cesare
    0.50
     Irak
    0.50
    dokument
    0.50
    pellier
    0.49
    musik
    0.49
    Activations Density 0.001%

    No Known Activations