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. 40-GEMMASCOPE-2-RES-262K
    4. 7337
    Prev
    Next
    INDEX
    Explanations

    mobile resolving module time post

    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
    ।”
    0.29
    Ꮬ
    0.28
    ൪
    0.28
    ished
    0.27
    ”।
    0.27
    いは
    0.27
    㛲
    0.26
    ’.”
    0.26
    हीत
    0.26
    isham
    0.26
    POSITIVE LOGITS
     इत्या
    0.27
     STILL
    0.23
     vẫn
    0.23
     dark
    0.23
     illegally
    0.23
     blah
    0.23
    ısının
    0.22
     extraordinaire
    0.22
     
    0.22
     Ups
    0.22
    Activations Density 0.196%

    No Known Activations