© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 57293
    Prev
    Next
    INDEX
    Explanations

    thanks for

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

    legal and ethical risks

    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
    封装
    0.52
    V
    0.51
    ви
    0.48
    𝙩
    0.46
    Machine
    0.45
    Capture
    0.45
     Rifle
    0.45
    W
    0.45
    M
    0.45
    Modifier
    0.44
    POSITIVE LOGITS
     novos
    0.52
     prowad
    0.52
     seguir
    0.51
    OLYBD
    0.51
     mostrou
    0.50
     minha
    0.50
     entendimento
    0.49
     colaboradores
    0.49
     fração
    0.49
     tratando
    0.48
    Activations Density 0.000%

    No Known Activations