© 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. 41-GEMMASCOPE-2-RES-262K
    7. 57967
    Prev
    Next
    INDEX
    Explanations

    date and units

    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_all/layer_41_width_262k_l0_big
    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
     langues
    0.40
     depictions
    0.39
    ∈
    0.38
    孃
    0.38
     couplers
    0.38
     rapor
    0.37
    ृत्व
    0.37
     formulations
    0.37
    дм
    0.37
     Μα
    0.36
    POSITIVE LOGITS
    ructor
    0.41
    augh
    0.39
    opian
    0.39
    oss
    0.38
    opolitan
    0.38
    虫
    0.38
     Oss
    0.38
    ocarp
    0.38
    ssen
    0.37
    ព
    0.37
    Activations Density 0.075%

    No Known Activations