© 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. 93075
    Prev
    Next
    INDEX
    Explanations

    Voß, VOS, Вос, Fos

    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
    promises
    -0.78
    焗
    -0.71
     compatriots
    -0.70
    fibre
    -0.69
    　　　　　　
    -0.69
     少
    -0.69
     />,
    -0.68
     Cahill
    -0.68
    Ժ
    -0.67
    뀐
    -0.67
    POSITIVE LOGITS
     вос
    0.84
     tecnológico
    0.77
    ESTON
    0.76
    ibili
    0.75
     accepts
    0.75
    cap
    0.74
     accept
    0.73
     Stück
    0.73
    oug
    0.73
    agang
    0.73
    Activations Density 0.024%

    No Known Activations