© 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. 10-GEMMASCOPE-RES-131K
    7. 119607
    Prev
    Next
    INDEX
    Explanations

    messing up something

    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_10/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
    髕
    -2.86
    𓆟
    -2.81
    鏷
    -2.70
     participado
    -2.63
    electricity
    -2.56
     überprü
    -2.48
     facendo
    -2.47
    你会
    -2.47
    燹
    -2.44
    郿
    -2.44
    POSITIVE LOGITS
    2
    2.41
    borderSide
    2.39
    on
    2.36
    providedIn
    2.34
    もありました
    2.06
    Various
    2.06
    or
    2.06
    7
    2.05
    –
    2.03
    隐隐
    2.02
    Activations Density 0.005%

    No Known Activations