© 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. 22-GEMMASCOPE-RES-131K
    7. 73074
    Prev
    Next
    INDEX
    Explanations

    specifications

    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
     they
    -1.26
     hjelpe
    -1.03
    лке
    -0.97
    Törté
    -0.93
    tım
    -0.92
    their
    -0.91
     even
    -0.89
    icht
    -0.89
     it
    -0.88
    会の
    -0.87
    POSITIVE LOGITS
     Perlu
    1.11
     uner
    0.98
    ourced
    0.96
     —
    0.94
     woj
    0.91
     reje
    0.91
     subje
    0.90
     finn
    0.90
     UIFont
    0.90
     alvo
    0.90
    Activations Density 0.030%

    No Known Activations