© 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. 2780
    Prev
    Next
    INDEX
    Explanations

    hidden things

    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
     Sinal
    -0.88
    絰
    -0.85
     interag
    -0.85
     verf
    -0.84
     ſta
    -0.80
     redire
    -0.80
    inige
    -0.79
     corrom
    -0.79
     かわいい
    -0.78
     engel
    -0.78
    POSITIVE LOGITS
     hidden
    1.34
     Hidden
    1.30
     dangers
    1.21
     treasure
    1.18
    hidden
    1.16
     beneath
    1.10
     gems
    1.09
     gem
    1.06
     secret
    1.05
     behind
    1.02
    Activations Density 0.015%

    No Known Activations