© 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. 1384
    Prev
    Next
    INDEX
    Explanations

    catapult to nomination, no reservations, this decision, public domain

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

    consumer, held, metric, storage, causes, collateral

    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
     inl
    0.48
     I
    0.48
     Ek
    0.46
     entfer
    0.46
     testifies
    0.46
     Oren
    0.44
     Hog
    0.43
     Ursula
    0.43
     feld
    0.42
     Riz
    0.42
    POSITIVE LOGITS
    راحی
    0.59
    lookup
    0.51
    transfected
    0.49
    ersi
    0.48
    変換
    0.47
    怨
    0.47
    pecific
    0.47
    traction
    0.47
    epy
    0.46
    raw
    0.46
    Activations Density 0.000%

    No Known Activations