© 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. 43488
    Prev
    Next
    INDEX
    Explanations

    predictive analytics

    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
     ನ್ಯಾಯ
    0.45
     infrequent
    0.40
    television
    0.40
    țiile
    0.39
    тельств
    0.39
    ilateral
    0.38
    <unused1100>
    0.38
     sixty
    0.38
    bracket
    0.38
    <unused100>
    0.38
    POSITIVE LOGITS
     máme
    0.52
     también
    0.50
     avem
    0.49
     produkter
    0.47
     Mga
    0.47
     Abbiamo
    0.47
     också
    0.46
     पनि
    0.46
    ก็
    0.45
     ook
    0.45
    Activations Density 0.002%

    No Known Activations