© 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. 34941
    Prev
    Next
    INDEX
    Explanations

    Names, titles, and company names

    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
    """,
    0.45
    CultureInfo
    0.45
    ал
    0.41
    >');
    0.41
     rameaux
    0.41
    ابعة
    0.41
    Imper
    0.40
     ‪
    0.40
    痂
    0.39
    """.
    0.38
    POSITIVE LOGITS
    s
    0.59
    self
    0.58
     SDF
    0.57
     Trudy
    0.54
    df
    0.52
    di
    0.52
     dosage
    0.52
     Wenger
    0.52
    萸
    0.51
     NPV
    0.49
    Activations Density 0.002%

    No Known Activations