© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32302
    Prev
    Next
    INDEX
    Explanations

    discussing past events and explanations

    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
     revered
    -1.34
     corret
    -1.31
     alcuni
    -1.24
     articulo
    -1.23
     nieuwe
    -1.23
     šķ
    -1.21
    訫
    -1.18
     realizzare
    -1.16
     astounding
    -1.16
     mystical
    -1.16
    POSITIVE LOGITS
     but
    2.58
     or
    1.92
     والتي
    1.84
     والذي
    1.55
     (
    1.47
     sondern
    1.43
     such
    1.38
     namely
    1.32
     provide
    1.31
     will
    1.30
    Activations Density 0.229%

    No Known Activations