© 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. 124361
    Prev
    Next
    INDEX
    Explanations

    market status and forecast

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

    distribution over words

    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
     pouquinho
    0.54
     overcomes
    0.53
    एल
    0.51
    ？](
    0.49
     جلسه
    0.46
    ]+
    0.46
    ]。
    0.46
    淡淡
    0.46
     }{}_{\
    0.45
     haunts
    0.45
    POSITIVE LOGITS
    isk
    0.57
    ération
    0.54
    share
    0.51
    ill
    0.49
    iki
    0.49
    fill
    0.48
    bowtie
    0.48
    ef
    0.47
    inois
    0.47
    discharge
    0.47
    Activations Density 0.000%

    No Known Activations