© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 231482
    Prev
    Next
    INDEX
    Explanations

    endodontic, term of, the teleporter, moon phases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ;
    0.47
    udio
    0.47
     Tablet
    0.44
     viêm
    0.44
     prostaglandin
    0.44
     Tablets
    0.43
    ())
    0.43
     शरीर
    0.42
     interstitial
    0.41
     internet
    0.40
    POSITIVE LOGITS
     आंब
    0.55
    ையுடன்
    0.55
    刈
    0.53
    ინი
    0.50
     devra
    0.50
    ით
    0.50
    ⴳ
    0.48
     doivent
    0.47
     Operated
    0.47
    ين
    0.47
    Activations Density 0.000%

    No Known Activations