© 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. 68530
    Prev
    Next
    INDEX
    Explanations

    transitioning between

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

    intuition and understanding

    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
    与其
    0.49
    సాయ
    0.48
    ཋ
    0.47
    璺
    0.46
    在她
    0.46
    翮
    0.45
     теат
    0.44
    เ
    0.44
    ﹗
    0.44
    忤
    0.44
    POSITIVE LOGITS
    4
    0.66
    3
    0.59
    2
    0.55
     U
    0.52
    6
    0.52
    ES
    0.52
    5
    0.50
    8
    0.50
    updated
    0.49
    ua
    0.49
    Activations Density 0.001%

    No Known Activations