© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118165
    Prev
    Next
    INDEX
    Explanations

    applicable law or

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    šené
    -0.73
    Algebra
    -0.68
    amboo
    -0.67
     стар
    -0.66
    必然
    -0.65
     posibilidad
    -0.65
     PUM
    -0.64
    BOW
    -0.64
     Cavaliers
    -0.64
     muslim
    -0.63
    POSITIVE LOGITS
    сек
    0.79
     Apache
    0.78
    ือก
    0.77
    hundreds
    0.76
     interrump
    0.75
     Heff
    0.72
     аз
    0.72
    vereins
    0.71
    DK
    0.69
    ffeine
    0.68
    Activations Density 0.062%

    No Known Activations