© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 203263
    Prev
    Next
    INDEX
    Explanations

    social scripts and APIs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ことができる
    0.46
    ↵↵
    0.43
     plonge
    0.42
     ترکیب
    0.42
    徵
    0.41
     горизонта
    0.41
    rement
    0.40
    (
    0.40
    これが
    0.40
    capable
    0.39
    POSITIVE LOGITS
    名稱
    0.49
    ikova
    0.45
     เหมาะ
    0.45
    гин
    0.45
     Raises
    0.43
    ：%
    0.42
     OUT
    0.41
     Thak
    0.41
     ，
    0.41
     undergoes
    0.41
    Activations Density 0.000%

    No Known Activations