© 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. 25802
    Prev
    Next
    INDEX
    Explanations

    random integer method calls

    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
     everything
    -1.41
     this
    -1.40
     then
    -1.31
     knows
    -1.27
     them
    -1.23
     that
    -1.19
     on
    -1.16
    从
    -1.16
     later
    -1.10
     way
    -1.07
    POSITIVE LOGITS
    apkamer
    1.20
    ージャー
    1.20
     لمدة
    1.19
     dorados
    1.16
     vache
    1.13
    Спасылкі
    1.12
    뭄
    1.10
     doktor
    1.09
     informe
    1.07
     mentale
    1.07
    Activations Density 0.002%

    No Known Activations