© 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-65K
    4. 2328
    Prev
    Next
    INDEX
    Explanations

    antioxidants or difficulties

    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_65k_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
     pituitary
    0.41
     जितनी
    0.40
    ="@+
    0.40
     similarly
    0.40
     pessimism
    0.39
    !\!\
    0.39
     spind
    0.39
     discernible
    0.39
    riek
    0.39
     Business
    0.37
    POSITIVE LOGITS
     adatto
    0.45
     പഴ
    0.43
     প্রাকৃতিক
    0.41
    こ
    0.41
     ricco
    0.41
     നന്ന
    0.41
    Meal
    0.40
     সারি
    0.39
     soupe
    0.39
     формат
    0.38
    Activations Density 0.008%

    No Known Activations