© 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. 8638
    Prev
    Next
    INDEX
    Explanations

    learning enemy patterns

    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
    ਟਰ
    0.51
    乆
    0.49
    ⵚ
    0.48
    拶
    0.47
     analogies
    0.47
    搆
    0.47
    ἆ
    0.47
    篒
    0.45
    亼
    0.45
    ને
    0.45
    POSITIVE LOGITS
    Landscape
    0.48
     في
    0.46
     در
    0.46
    city
    0.46
     in
    0.45
    guide
    0.44
    );
    0.42
    Malformed
    0.42
    degenerative
    0.42
    Region
    0.42
    Activations Density 0.006%

    No Known Activations