© 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. 163472
    Prev
    Next
    INDEX
    Explanations

    administration service

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

    experiment, understanding, trivial, kill, World, independent, ext, number

    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
    铠
    0.45
     snelheid
    0.44
     authenticate
    0.43
     statistique
    0.43
    (&:
    0.43
    preprocess
    0.43
     armour
    0.42
     slij
    0.42
     byl
    0.42
    POSITIVE LOGITS
    휋
    0.50
    analisi
    0.46
    rafpunkte
    0.46
    ֛
    0.45
    ada
    0.44
    ra
    0.43
    定め
    0.43
    чему
    0.43
    는데
    0.42
     outcomes
    0.42
    Activations Density 0.000%

    No Known Activations