© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 65696
    Prev
    Next
    INDEX
    Explanations

    without notice

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

    vowel sounds

    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
     rootView
    0.46
    ?,?,
    0.45
     switchTo
    0.43
    setP
    0.43
    ዚያ
    0.43
    疮
    0.42
    能力的
    0.42
    龙
    0.42
    **************
    0.41
     코드
    0.41
    POSITIVE LOGITS
    nt
    0.45
    Timing
    0.43
    Approx
    0.42
    飛
    0.41
    }$)
    0.41
    PropertyName
    0.41
    nr
    0.40
     Bör
    0.40
     czek
    0.40
    Registration
    0.39
    Activations Density 0.000%

    No Known Activations