© 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. 12254
    Prev
    Next
    INDEX
    Explanations

    river names and locations

    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
     intolerable
    0.46
     formidable
    0.46
     consapevole
    0.44
     refug
    0.43
     elas
    0.42
     amts
    0.42
     mailed
    0.42
     種
    0.41
    ，「
    0.41
     regia
    0.40
    POSITIVE LOGITS
    DSP
    0.43
    Heinrich
    0.42
    Measurement
    0.40
    Redis
    0.40
    Cork
    0.39
    kten
    0.38
    <=>
    0.38
    Bristol
    0.38
    羁
    0.38
    Dimensional
    0.38
    Activations Density 0.053%

    No Known Activations