© 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. 91746
    Prev
    Next
    INDEX
    Explanations

    caravan heads, caravans of, loss, debuted, card, DI

    np_acts-logits-general · gemini-2.5-flash-lite

    essential saving very channel

    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
    ARE
    0.43
    FAC
    0.43
    т
    0.43
     स्वत
    0.43
     salesmen
    0.42
     hairy
    0.42
    BERT
    0.41
     SMEs
    0.41
    嗯
    0.41
     Hort
    0.40
    POSITIVE LOGITS
    রার
    0.57
     gyakor
    0.52
    kowej
    0.49
     mogelijk
    0.49
     opnieuw
    0.49
     alumno
    0.48
     konflikt
    0.48
     ży
    0.47
     ల
    0.47
     to
    0.46
    Activations Density 0.000%

    No Known Activations