© 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. 168461
    Prev
    Next
    INDEX
    Explanations

    property keywords

    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
     monstru
    0.40
    ﺿ
    0.40
     absolutamente
    0.40
    挖掘
    0.39
     vinos
    0.39
    தமான
    0.38
    сто
    0.38
    ின்றான்
    0.37
     preparar
    0.37
    葡
    0.37
    POSITIVE LOGITS
    áp
    0.38
    uttered
    0.38
    rowned
    0.38
    locked
    0.36
    ätte
    0.36
    ัป
    0.36
     Trusted
    0.36
     Couch
    0.36
     పట్ట
    0.35
     売
    0.35
    Activations Density 0.001%

    No Known Activations