© 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. 34-GEMMASCOPE-RES-131K
    7. 63622
    Prev
    Next
    INDEX
    Explanations

    legal and scientific contexts

    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_34/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
     двигателя
    -0.75
    msleep
    -0.74
     async
    -0.73
     historic
    -0.73
    νω
    -0.71
     Ress
    -0.71
    ilkan
    -0.69
     cm
    -0.69
     Guyana
    -0.69
     stoop
    -0.69
    POSITIVE LOGITS
    之处
    0.91
     zitate
    0.82
     particuliers
    0.82
    父亲
    0.80
     förra
    0.79
     CHICKEN
    0.78
     stammen
    0.77
     têtes
    0.76
     prête
    0.75
    ceutical
    0.75
    Activations Density 0.007%

    No Known Activations