© 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. 148056
    Prev
    Next
    INDEX
    Explanations

    aim to get / value system / result recalibrate

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

    imagine creating a list

    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
    ەکە
    0.46
    ہوں
    0.43
     Broadband
    0.43
    sü
    0.42
    भात
    0.41
    वण्यासाठी
    0.41
    からです
    0.41
    ～～
    0.40
    மேலும்
    0.40
     রিসার্চ
    0.40
    POSITIVE LOGITS
    řad
    0.49
     шла
    0.47
     commiss
    0.47
    Instance
    0.46
    setType
    0.46
    кли
    0.46
    тов
    0.45
    No
    0.45
    лев
    0.45
    ститут
    0.44
    Activations Density 0.001%

    No Known Activations