© 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. 143668
    Prev
    Next
    INDEX
    Explanations

    programming environments, automation, TTS

    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
    ტორი
    0.60
    靝
    0.55
    䒺
    0.54
    லோக
    0.52
     ट्र
    0.52
    OrderFlight
    0.51
    ტის
    0.51
    Ⴊ
    0.51
    modulin
    0.49
     त्यांची
    0.48
    POSITIVE LOGITS
     conductor
    0.47
     stage
    0.45
     scoop
    0.44
    末
    0.43
     diter
    0.42
     classroom
    0.41
    0
    0.41
     bathroom
    0.41
     scorer
    0.41
     language
    0.40
    Activations Density 0.001%

    No Known Activations