© 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. 40-GEMMASCOPE-2-RES-262K
    7. 195518
    Prev
    Next
    INDEX
    Explanations

    everyone feels

    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
     highly
    0.41
    เป
    0.41
     miejsce
    0.41
     acaso
    0.40
     deliberate
    0.39
     place
    0.38
    陉
    0.37
     disastrous
    0.37
    highly
    0.36
     Highly
    0.36
    POSITIVE LOGITS
    Exclude
    0.36
    締
    0.35
     tou
    0.35
     Camacho
    0.35
     thrott
    0.35
     ParkingLot
    0.35
    赳
    0.35
    weit
    0.35
    <0xB6>
    0.34
     досто
    0.34
    Activations Density 0.000%

    No Known Activations