© 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. 11966
    Prev
    Next
    INDEX
    Explanations

    Discord servers and voice channels

    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
     arginine
    0.42
     tobacco
    0.40
     апо
    0.38
     ecu
    0.38
    phins
    0.38
     Physician
    0.38
    alassemia
    0.38
    胗
    0.38
     Echin
    0.38
     Tobacco
    0.37
    POSITIVE LOGITS
     Discord
    1.48
    Discord
    1.41
     discord
    1.33
    discord
    1.23
     Nitro
    0.82
    Guild
    0.81
    Nitro
    0.79
     guilds
    0.75
     discordant
    0.74
    guild
    0.73
    Activations Density 0.021%

    No Known Activations