Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 1159
    Prev
    Next
    INDEX
    Explanations

    brainstorming and testing actions

    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
     of
    0.25
     Raman
    0.22
     UNESCO
    0.22
     Buddhist
    0.21
     Islamic
    0.21
    S
    0.21
     I
    0.21
     Ä
    0.20
    son
    0.20
     de
    0.20
    POSITIVE LOGITS
     accordingly
    0.27
     עם
    0.25
     بها
    0.25
     với
    0.25
     with
    0.25
     avec
    0.24
     svůj
    0.24
     себе
    0.24
     ně
    0.23
     cosas
    0.23
    Activations Density 0.847%

    No Known Activations