© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 49409
    Prev
    Next
    INDEX
    Explanations

    majority of, along the, LDS Family, mentioned a, We pride, by another

    np_acts-logits-general · gemini-2.5-flash-lite

    English phrases or specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MON
    0.52
    사
    0.50
    MAKE
    0.49
    은
    0.48
     MON
    0.48
    IT
    0.47
    ON
    0.47
    登
    0.47
    Na
    0.46
    이
    0.46
    POSITIVE LOGITS
     supremacist
    0.44
     трево
    0.43
     liturg
    0.43
     McEl
    0.42
     nabí
    0.42
     Todd
    0.42
     Cullen
    0.40
     خطا
    0.40
     covenant
    0.40
     mérid
    0.40
    Activations Density 0.000%

    No Known Activations