© 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. 23628
    Prev
    Next
    INDEX
    Explanations

    asking for action or information

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

    water condensation and leaks

    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
    內
    0.51
     I
    0.48
    内
    0.45
     scalar
    0.45
    귤
    0.43
     ठर
    0.42
    判
    0.42
    ős
    0.40
    下
    0.39
    字符串
    0.38
    POSITIVE LOGITS
     Practitioner
    0.54
     :,
    0.54
     Practical
    0.52
    thorax
    0.51
    dimensioni
    0.51
    Practical
    0.50
    shoot
    0.50
    laying
    0.48
     pestaña
    0.48
     ადგილ
    0.47
    Activations Density 0.000%

    No Known Activations