© 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. 41863
    Prev
    Next
    INDEX
    Explanations

    style attributes

    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
    拶
    -1.77
    聼
    -1.53
     ogrom
    -1.49
     проє
    -1.45
    鴣
    -1.44
     durumda
    -1.39
     costumbres
    -1.35
     />
    -1.35
    ло
    -1.35
     wüns
    -1.34
    POSITIVE LOGITS
    媄
    1.77
    they
    1.60
     melap
    1.51
    鈊
    1.50
    This
    1.48
     utk
    1.45
     tasche
    1.45
     kafe
    1.44
     karbon
    1.44
     kredit
    1.44
    Activations Density 0.015%

    No Known Activations