© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 100136
    Prev
    Next
    INDEX
    Explanations

    scientist papers entry confidential

    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
     disciplined
    0.45
    恜
    0.40
     геометри
    0.40
    )){
    0.39
    😲
    0.38
     যেখানে
    0.38
     coveredmethods
    0.38
     discipl
    0.38
    ({\
    0.38
     innym
    0.38
    POSITIVE LOGITS
    timeslots
    0.40
    fee
    0.39
     Format
    0.38
    incarn
    0.38
     देणे
    0.38
     스테
    0.38
     दिये
    0.36
     하나의
    0.36
    unlock
    0.35
     ООО
    0.35
    Activations Density 0.000%

    No Known Activations