© 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. 36534
    Prev
    Next
    INDEX
    Explanations

    mathematical and scientific concepts

    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
    愘
    0.43
    嗉
    0.42
    袴
    0.41
     Ç
    0.40
    镞
    0.40
     доступ
    0.39
     ഗു
    0.39
     templates
    0.39
     UConn
    0.39
    㤟
    0.39
    POSITIVE LOGITS
    ("/
    0.36
    Monday
    0.36
    Hoy
    0.36
    RewardedVideo
    0.36
    ("/")
    0.35
    Ling
    0.35
     parum
    0.35
    ניה
    0.35
     túl
    0.35
    izam
    0.34
    Activations Density 0.000%

    No Known Activations