© 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-262K
    7. 2598
    Prev
    Next
    INDEX
    Explanations

    developer resource URLs

    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
     металла
    0.43
    🏥
    0.42
    💐
    0.41
     كوب
    0.40
    ᆭ
    0.39
    🚺
    0.38
     biodegradation
    0.38
    LastGen
    0.38
    🤱
    0.38
    COMANDA
    0.38
    POSITIVE LOGITS
    github
    1.10
     github
    0.93
     GitHub
    0.89
    www
    0.83
     Github
    0.80
    GitHub
    0.78
    developer
    0.77
     developer
    0.77
    developers
    0.74
     developers
    0.73
    Activations Density 0.007%

    No Known Activations