© 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. 1494
    Prev
    Next
    INDEX
    Explanations

    in component health

    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
    杓
    0.38
    Defaults
    0.37
    ופי
    0.37
    odis
    0.36
    ἢ
    0.36
    வடிக்க
    0.36
    auri
    0.35
    бе
    0.34
    ød
    0.34
    गण
    0.34
    POSITIVE LOGITS
    VPN
    0.44
    ฀
    0.43
     PLAY
    0.41
     動画
    0.40
     }}>
    0.40
    deter
    0.40
     KILL
    0.40
    ,_-
    0.40
     errores
    0.39
     OVER
    0.39
    Activations Density 0.000%

    No Known Activations