© 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. 11818
    Prev
    Next
    INDEX
    Explanations

    URLs ending in slash

    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
     creature
    0.42
     cray
    0.42
    倨
    0.41
     bow
    0.39
     giddy
    0.39
     Southwestern
    0.39
     crown
    0.38
     vie
    0.38
    vee
    0.38
     stationary
    0.38
    POSITIVE LOGITS
     మాట్లాడుతూ
    0.39
     منفی
    0.38
     tecniche
    0.36
    乇
    0.36
    érapie
    0.36
     Therapie
    0.35
    blogs
    0.35
     бесплат
    0.35
     ಸಂ
    0.35
    ]={
    0.35
    Activations Density 0.000%

    No Known Activations