© 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. 151947
    Prev
    Next
    INDEX
    Explanations

    professional staff

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

    prevents back, easily skip, a brand

    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
     perintah
    0.50
    ᒫ
    0.46
     ekonomik
    0.46
     audiovis
    0.45
     esempl
    0.44
    LSTM
    0.44
     inverso
    0.44
     attaqu
    0.44
    s
    0.44
    lios
    0.43
    POSITIVE LOGITS
     nanny
    0.49
     chiropractor
    0.45
    ेने
    0.45
     Camille
    0.44
     Nouveau
    0.43
     tummy
    0.43
    ারে
    0.42
    ছনে
    0.42
    ঢ়
    0.41
     campaigning
    0.40
    Activations Density 0.000%

    No Known Activations