© 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. 34-GEMMASCOPE-RES-131K
    7. 78342
    Prev
    Next
    INDEX
    Explanations

    crypto, RSA, proof

    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_34/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
     aban
    -0.78
    看去
    -0.76
     contrary
    -0.76
     Nego
    -0.74
    婊
    -0.72
    cemia
    -0.71
     ()
    -0.71
    nego
    -0.71
    hanced
    -0.71
    Chloro
    -0.71
    POSITIVE LOGITS
    Proof
    0.93
     Proof
    0.88
    Westfalen
    0.80
    Signature
    0.75
     proof
    0.75
    Signatures
    0.74
     signatures
    0.73
    Hrsg
    0.73
     Humanities
    0.72
    PROOF
    0.72
    Activations Density 0.001%

    No Known Activations