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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 52890
    Prev
    Next
    INDEX
    Explanations

    tail excitedly

    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_65k_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
    ज़ार
    0.44
    Insider
    0.42
    Pension
    0.41
    Governance
    0.41
    CompanyName
    0.40
    庤
    0.39
    Inicial
    0.39
    Leather
    0.38
    Boris
    0.38
    庣
    0.38
    POSITIVE LOGITS
     Session
    0.40
     session
    0.38
     stamps
    0.37
     Excited
    0.37
     French
    0.37
     RPG
    0.37
     Stamp
    0.37
     arrang
    0.37
     OL
    0.37
     postage
    0.36
    Activations Density 0.001%

    No Known Activations