© 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. 195459
    Prev
    Next
    INDEX
    Explanations

    indicator of markets world Rosetta stone

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

    simplify the

    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
    ayev
    0.53
    erin
    0.51
     문제를
    0.50
    lin
    0.50
    huy
    0.49
    hor
    0.46
    jour
    0.45
    纍
    0.45
    ሪ
    0.45
     könne
    0.45
    POSITIVE LOGITS
    XH
    0.44
     অস্থ
    0.43
    шти
    0.43
    карбо
    0.43
    триму
    0.42
     Само
    0.42
     steamed
    0.42
     masculine
    0.42
     delight
    0.40
     HSP
    0.40
    Activations Density 0.000%

    No Known Activations