© 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. 128841
    Prev
    Next
    INDEX
    Explanations

    API request results

    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
    umers
    -1.16
    手腕
    -1.10
    を変える
    -1.09
     Cancelar
    -1.07
    
    -1.05
     malattie
    -1.05
    ricle
    -1.05
     nuove
    -1.04
     strategie
    -1.02
     volverá
    -1.02
    POSITIVE LOGITS
     result
    1.05
     尼
    1.02
    さまざま
    0.99
    result
    0.95
    NTSTATUS
    0.91
    様々
    0.91
     process
    0.91
     outcome
    0.90
    amazonaws
    0.89
     vieilles
    0.89
    Activations Density 0.005%

    No Known Activations