© 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. 51267
    Prev
    Next
    INDEX
    Explanations

    building floor meter

    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
    antlr
    0.43
     रखिए
    0.43
     உண்மையில்
    0.42
    襦
    0.42
    okatokat
    0.42
     बुला
    0.42
     BVHTree
    0.42
    舎
    0.42
     వచ్చిన
    0.41
    蝿
    0.41
    POSITIVE LOGITS
     â
    0.41
     poles
    0.39
    th
    0.39
    iques
    0.37
    â
    0.36
     met
    0.35
     meter
    0.35
     spokes
    0.35
    Р
    0.35
    ag
    0.35
    Activations Density 0.037%

    No Known Activations