© 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. 22-GEMMASCOPE-RES-131K
    7. 33209
    Prev
    Next
    INDEX
    Explanations

    increase in number or use

    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_22/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
     may
    -1.45
     or
    -1.31
     апре
    -1.13
    _{\
    -1.12
     từng
    -1.10
    {\
    -1.09
    ėjo
    -1.07
    儘
    -1.07
     localidad
    -1.06
     might
    -1.05
    POSITIVE LOGITS
    Both
    1.48
     både
    1.27
     diskusi
    1.09
    selben
    1.09
    雰囲
    1.08
     raste
    1.06
     centru
    1.06
    latter
    1.06
     in
    1.05
     剑
    1.05
    Activations Density 0.118%

    No Known Activations