© 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. 111135
    Prev
    Next
    INDEX
    Explanations

    damage to intestinal wall

    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
     spasms
    0.47
     conditioners
    0.47
     utilisent
    0.47
    𒈾
    0.45
     exacerbate
    0.44
    ພວກເຮົາ
    0.44
     Apartments
    0.44
     ligaments
    0.43
    赂
    0.43
     υπό
    0.43
    POSITIVE LOGITS
     л
    0.45
    </th>
    0.44
     сигнал
    0.43
    annotate
    0.42
    Serializable
    0.42
    quam
    0.39
    AS
    0.39
     tehdä
    0.39
    зать
    0.38
    omar
    0.38
    Activations Density 0.002%

    No Known Activations