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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 165356
    Prev
    Next
    INDEX
    Explanations

    programming and diverse topics

    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_40_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
     +/-
    0.39
    opacity
    0.38
    នោះ
    0.38
     anal
    0.37
     ф
    0.37
     보다
    0.37
    @
    0.36
    も含
    0.35
     unit
    0.35
     عملکرد
    0.35
    POSITIVE LOGITS
     imposible
    0.45
    贿
    0.44
    性感
    0.43
     immoral
    0.42
    ał
    0.41
     humili
    0.40
     WHIT
    0.40
     seldom
    0.40
     URANIUM
    0.40
     prostit
    0.40
    Activations Density 0.001%

    No Known Activations