© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71723
    Prev
    Next
    INDEX
    Explanations

    phone numbers and codes

    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
     feitos
    -1.75
    ńst
    -1.52
     anunciado
    -1.50
     Dernière
    -1.47
     éclairage
    -1.46
    スコア
    -1.46
     motivadoras
    -1.40
     citada
    -1.40
     whichever
    -1.34
    oodoo
    -1.33
    POSITIVE LOGITS
     more
    2.05
    9
    1.90
    7
    1.81
    1
    1.65
    8
    1.64
    3
    1.63
     not
    1.63
    4
    1.61
    5
    1.60
     actual
    1.59
    Activations Density 0.023%

    No Known Activations