© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 85148
    Prev
    Next
    INDEX
    Explanations

    originalism, late, educators, settled

    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
    ೭
    0.38
     حول
    0.38
    品番
    0.38
    Communications
    0.38
    !');
    0.37
    }!
    0.37
     กี้
    0.36
    <unused2031>
    0.36
    !");
    0.36
    ケース
    0.36
    POSITIVE LOGITS
    DOL
    0.44
    dol
    0.38
     Thermodynamics
    0.38
    URAL
    0.38
     различных
    0.38
    cors
    0.38
    缅
    0.38
    GOR
    0.38
     orthopedic
    0.38
     various
    0.37
    Activations Density 0.000%

    No Known Activations