© 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. 35967
    Prev
    Next
    INDEX
    Explanations

    need to get

    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
     구매
    0.42
    जेक्ट
    0.41
    Чита
    0.40
    Comunic
    0.40
     Kommunikation
    0.39
    黢
    0.39
     ლი
    0.38
    💻
    0.38
     படிக்க
    0.38
    Aut
    0.38
    POSITIVE LOGITS
     hierro
    0.44
     returns
    0.42
     relaxed
    0.42
     Copper
    0.42
     related
    0.41
     die
    0.41
     Crisp
    0.41
     represented
    0.41
     =
    0.41
    0.40
    Activations Density 0.014%

    No Known Activations