© 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. 34-GEMMASCOPE-RES-131K
    7. 1020
    Prev
    Next
    INDEX
    Explanations

    Morocco, Liviu

    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
    ivoli
    -0.67
    Eqn
    -0.66
     upro
    -0.66
    жливо
    -0.65
     مشين
    -0.65
    Outgoing
    -0.65
    Carole
    -0.65
     штат
    -0.64
    vela
    -0.64
     WIP
    -0.64
    POSITIVE LOGITS
     versioni
    0.99
    DateTime
    0.88
     Pelle
    0.85
    DateTimeField
    0.85
     procé
    0.85
    ارو
    0.82
    SOFTWARE
    0.81
     cubierta
    0.79
     totals
    0.79
     atmósfera
    0.78
    Activations Density 0.018%

    No Known Activations