© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40404
    Prev
    Next
    INDEX
    Explanations

    singleton, static, class

    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
    There
    -1.55
     there
    -1.45
     my
    -1.41
     myself
    -1.38
     Terkait
    -1.28
    there
    -1.25
    If
    -1.21
    また
    -1.16
     resulting
    -1.11
     including
    -1.08
    POSITIVE LOGITS
     saveurs
    1.50
     ourselves
    1.41
    圪
    1.36
    が少ない
    1.28
     alá
    1.28
     leurs
    1.25
     collective
    1.24
     conozco
    1.21
    namese
    1.19
     larmes
    1.18
    Activations Density 0.044%

    No Known Activations