© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 32004
    Prev
    Next
    INDEX
    Explanations

    window cleaning

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

    objects where not

    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
     सावधानी
    0.50
    лась
    0.49
    istic
    0.49
    nosti
    0.49
    ley
    0.48
    接続
    0.47
    ¢
    0.47
    间隔
    0.46
    iley
    0.46
    rives
    0.46
    POSITIVE LOGITS
     própri
    0.50
     ZO
    0.49
     KLM
    0.49
     akad
    0.48
     ibis
    0.47
     kong
    0.47
    AVOA
    0.47
     VALLEY
    0.46
     KJ
    0.46
     nitrogen
    0.45
    Activations Density 0.001%

    No Known Activations