© 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. 106973
    Prev
    Next
    INDEX
    Explanations

    Serial coupling, Fender Vibratone

    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
     perhaps
    -0.79
     Betrachtung
    -0.76
    @",
    -0.71
    Види
    -0.71
     eh
    -0.71
     directly
    -0.69
     gewährle
    -0.69
    ധ
    -0.68
     conventional
    -0.68
     foi
    -0.67
    POSITIVE LOGITS
    Spent
    0.91
     dét
    0.91
    )}-\
    0.88
     arrêté
    0.82
    }-\
    0.81
    essed
    0.81
     meub
    0.79
    香蕉
    0.79
    still
    0.78
    VING
    0.78
    Activations Density 0.009%

    No Known Activations