© 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. 117063
    Prev
    Next
    INDEX
    Explanations

    making a point

    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
    พาะ
    -0.82
    ɵɵelementEnd
    -0.81
     Describe
    -0.81
    LOPT
    -0.77
     Describes
    -0.73
     Empfehlungen
    -0.73
     Goodrich
    -0.73
     lesen
    -0.72
    álna
    -0.72
    Vue
    -0.71
    POSITIVE LOGITS
     pointed
    5.38
     pointing
    4.78
     point
    4.28
    pointed
    3.84
    pointing
    3.75
     Point
    3.56
    Point
    3.47
    point
    3.34
     POINT
    3.33
     points
    3.31
    Activations Density 0.086%

    No Known Activations