© 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. 22-GEMMASCOPE-RES-131K
    7. 14558
    Prev
    Next
    INDEX
    Explanations

    last occurrence in code

    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
     with
    -1.14
     Popis
    -1.13
     of
    -1.02
    hiasan
    -1.02
    ervous
    -1.01
     from
    -1.00
     semplicemente
    -1.00
    ﻊ
    -0.99
     even
    -0.99
     monumentos
    -0.98
    POSITIVE LOGITS
    brtc
    1.20
    gemeester
    1.14
     (;;
    1.12
     NEEDED
    1.09
    了两
    1.08
     scena
    1.08
    woners
    1.06
    ajuku
    1.06
     metri
    1.05
     inplace
    1.05
    Activations Density 0.019%

    No Known Activations