© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 200439
    Prev
    Next
    INDEX
    Explanations

    I've focused on detailing

    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
    DR
    0.49
    ف
    0.48
    بر
    0.47
    Only
    0.47
    instruction
    0.47
    도
    0.46
    ほ
    0.46
    тель
    0.46
    d
    0.45
    City
    0.44
    POSITIVE LOGITS
     इंट्रो
    0.51
     músico
    0.50
     Coleoptera
    0.48
    सदीय
    0.48
     Wochschr
    0.47
     Yukawa
    0.46
     увиде
    0.45
     фаразлау
    0.44
     Pourquoi
    0.44
     ProRes
    0.44
    Activations Density 0.004%

    No Known Activations