© 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. 139461
    Prev
    Next
    INDEX
    Explanations

    your property

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

    original model weights

    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
     twor
    0.48
    কার্য
    0.46
     sensitized
    0.45
    없
    0.44
    ridges
    0.43
     perust
    0.43
    రించ
    0.43
     നിങ്ങൾ
    0.42
    炇
    0.42
     sensitization
    0.42
    POSITIVE LOGITS
     रुका
    0.45
    HttpStatusCode
    0.41
     complicada
    0.41
     زیادہ
    0.39
    iku
    0.39
     excepciones
    0.39
    どこ
    0.38
     Большая
    0.38
    ೆಂಟ್
    0.38
     Crac
    0.38
    Activations Density 0.001%

    No Known Activations