© 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. 26031
    Prev
    Next
    INDEX
    Explanations

    programming code constructs

    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
     abgerufen
    -1.37
    </tfoot>
    -1.30
     ними
    -1.26
    门外
    -1.13
     them
    -1.13
    EdgeInsets
    -1.13
    ኧ
    -1.11
    HideFlags
    -1.10
     Fürsten
    -1.09
    //{
    -1.08
    POSITIVE LOGITS
    ↵
    1.58
    甭
    1.13
     Añade
    1.09
     Selecciona
    1.09
     markiert
    1.09
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.08
     prépare
    1.08
    .
    1.05
    0
    1.05
    齎
    1.05
    Activations Density 0.000%

    No Known Activations