© 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. 139043
    Prev
    Next
    INDEX
    Explanations

    Proper nouns and non-English characters

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

    while clauses

    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
    ジナル
    0.50
    irrah
    0.49
     ولي
    0.46
     배웠
    0.46
     terv
    0.45
    ㎛
    0.45
     உயரம்
    0.45
     사례
    0.45
     ဝ
    0.44
    ino
    0.43
    POSITIVE LOGITS
    ה
    0.52
    нил
    0.48
    Aston
    0.46
    Sunday
    0.45
    PickerDialog
    0.45
    eaa
    0.44
    ঁয়
    0.43
    撳
    0.43
    组合
    0.43
    Exclusive
    0.43
    Activations Density 0.000%

    No Known Activations