© 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. 22-GEMMASCOPE-RES-131K
    7. 26178
    Prev
    Next
    INDEX
    Explanations

    boolean flags or values

    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_22/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
    了很多
    -1.77
     the
    -1.63
    {
    -1.60
    -
    -1.58
     provocó
    -1.52
    にします
    -1.44
    的で
    -1.41
     This
    -1.39
     Thus
    -1.38
    に入れる
    -1.36
    POSITIVE LOGITS
    🫃
    1.55
     atencion
    1.53
     plafon
    1.52
     poliuret
    1.50
    érape
    1.48
     mentale
    1.47
     mentales
    1.47
     visuel
    1.45
     direccion
    1.44
     anormal
    1.44
    Activations Density 0.016%

    No Known Activations