© 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. 34-GEMMASCOPE-RES-131K
    7. 81309
    Prev
    Next
    INDEX
    Explanations

    cracking and deciphering 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_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
    監
    -0.84
    squareup
    -0.78
    朗
    -0.74
    框
    -0.72
    utorial
    -0.72
    יים
    -0.71
    Acest
    -0.71
    chro
    -0.70
    Defining
    -0.70
    Introducing
    -0.70
    POSITIVE LOGITS
     code
    3.70
     coded
    3.56
     codes
    3.16
    code
    2.95
    coded
    2.92
     código
    2.64
     encoded
    2.58
    codes
    2.56
     Code
    2.48
    Code
    2.42
    Activations Density 0.073%

    No Known Activations