© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 103711
    Prev
    Next
    INDEX
    Explanations

    must-have, must-read, must-see

    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
    fillment
    -1.00
     ASR
    -1.00
    según
    -0.98
    mindedness
    -0.95
    timmung
    -0.95
    theless
    -0.93
    沨
    -0.92
    𝖮
    -0.91
    füllung
    -0.90
    Uris
    -0.90
    POSITIVE LOGITS
     must
    1.43
     Must
    1.28
    must
    1.25
    Must
    1.23
    Have
    1.16
     needed
    1.14
     for
    1.03
     have
    1.02
     MUST
    1.02
     not
    0.97
    Activations Density 0.007%

    No Known Activations