© 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. 10-GEMMASCOPE-RES-131K
    7. 100293
    Prev
    Next
    INDEX
    Explanations

    drilling and holes

    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_10/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
     certaines
    -1.71
     certains
    -1.62
    u
    -1.57
     letzten
    -1.54
    VISED
    -1.30
     ۷
    -1.20
     derniers
    -1.20
     craz
    -1.16
    ・・・」
    -1.15
     während
    -1.14
    POSITIVE LOGITS
     holes
    1.68
     for
    1.63
    ).
    1.56
     because
    1.56
     What
    1.55
    }$.
    1.46
     How
    1.44
     through
    1.44
     hole
    1.42
     from
    1.38
    Activations Density 0.144%

    No Known Activations