© 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. 4045
    Prev
    Next
    INDEX
    Explanations

    problematic scenarios

    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
     the
    0.44
    ad
    0.42
     be
    0.42
    f
    0.42
     imported
    0.41
     Westport
    0.41
     $\
    0.41
     \
    0.40
     textiles
    0.40
     yh
    0.40
    POSITIVE LOGITS
     також
    0.45
    此事
    0.45
    caso
    0.44
     தன்
    0.44
    క్త
    0.43
    CISE
    0.43
     riguardo
    0.42
    й
    0.42
    ８
    0.42
    まず
    0.42
    Activations Density 0.210%

    No Known Activations