© 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. 32784
    Prev
    Next
    INDEX
    Explanations

    we may / retired people / their time

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

    attacks, entitlement, emergence

    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
    ،
    0.46
     phosphor
    0.44
     thiaz
    0.44
     zar
    0.44
     glutathione
    0.43
     hydrogen
    0.43
     chocolate
    0.42
     diaz
    0.42
     mich
    0.42
    хра
    0.42
    POSITIVE LOGITS
    Variation
    0.54
    㠻
    0.54
    ående
    0.52
    õ
    0.50
    Return
    0.49
    yscrapers
    0.49
    prü
    0.48
    yr
    0.48
    itoti
    0.48
    ycz
    0.48
    Activations Density 0.000%

    No Known Activations