© 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. 71494
    Prev
    Next
    INDEX
    Explanations

    Meta AI, absurdity, fade

    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
     infection
    0.45
     malaria
    0.42
     microbiome
    0.42
     myeloma
    0.42
     worldRank
    0.42
     acne
    0.42
    ↵↵
    0.41
     infections
    0.41
     mountains
    0.41
     NDVI
    0.40
    POSITIVE LOGITS
     quizá
    0.47
    acán
    0.45
    úan
    0.43
    íticos
    0.42
     లేదా
    0.42
    ján
    0.42
    ágoras
    0.42
     niektor
    0.42
    juna
    0.41
    <unused1882>
    0.41
    Activations Density 0.009%

    No Known Activations