© 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. 40016
    Prev
    Next
    INDEX
    Explanations

    http and https URLs

    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
    ">
    -1.21
    шки
    -1.17
     Bet
    -1.16
     iyon
    -1.15
    дка
    -1.15
    .«
    -1.15
    ique
    -1.13
     who
    -1.13
     Starts
    -1.13
    entown
    -1.13
    POSITIVE LOGITS
     Ofrece
    1.24
     solchen
    1.23
    brania
    1.20
    姈
    1.20
    ))$_
    1.11
     powdery
    1.09
     Aseg
    1.08
     greatest
    1.08
     sogenannten
    1.08
     predominate
    1.07
    Activations Density 0.286%

    No Known Activations