© 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. 22-GEMMASCOPE-RES-131K
    7. 39602
    Prev
    Next
    INDEX
    Explanations

    hexadecimal numbers and identifiers

    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
    NewLabel
    -1.09
    banden
    -1.02
     misma
    -1.02
     such
    -0.99
    matta
    -0.97
     same
    -0.96
    various
    -0.96
    νομ
    -0.93
    اهش
    -0.90
    CreatedBy
    -0.90
    POSITIVE LOGITS
     Describes
    0.92
     physiques
    0.90
     Descrip
    0.90
     Siles
    0.89
     Relaxation
    0.89
    昨日は
    0.87
     sels
    0.86
     everyone
    0.85
     sehe
    0.84
     гром
    0.84
    Activations Density 0.008%

    No Known Activations