© 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-65K
    7. 27995
    Prev
    Next
    INDEX
    Explanations

    describing changes and arrangements

    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
     önce
    0.51
     ആദ്യം
    0.51
     początku
    0.45
    一开始
    0.44
     প্রথমে
    0.44
    cheidet
    0.42
     முதலில்
    0.42
     często
    0.42
     Sereth
    0.41
     şöyle
    0.40
    POSITIVE LOGITS
     misdemeanor
    0.47
    5
    0.46
     enforceable
    0.46
     unfairly
    0.46
     culpa
    0.45
     meaningfully
    0.44
     webinars
    0.44
    participation
    0.43
     insignificant
    0.43
     webinar
    0.42
    Activations Density 0.034%

    No Known Activations