© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 28127
    Prev
    Next
    INDEX
    Explanations

    Flask request code

    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
    י
    0.56
    ה
    0.47
    ه
    0.46
    ي
    0.45
    время
    0.42
    со
    0.42
    то
    0.42
    સ
    0.41
    ਿ
    0.41
    urilor
    0.41
    POSITIVE LOGITS
     proceedings
    0.43
     alten
    0.43
     literatura
    0.41
     anschließend
    0.40
    amped
    0.40
     beteiligt
    0.40
     zijn
    0.40
    ávají
    0.40
     int
    0.39
     aktive
    0.39
    Activations Density 0.003%

    No Known Activations