© 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. 91564
    Prev
    Next
    INDEX
    Explanations

    physical appearance and afflictions

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

    physical wear and tear

    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
    áž
    0.53
    تمي
    0.48
     قطعة
    0.46
    Ultr
    0.46
     ఏర్ప
    0.46
    })^{\
    0.45
     אר
    0.45
    }]$.
    0.45
     দাবী
    0.44
    Obst
    0.44
    POSITIVE LOGITS
     bruises
    0.52
     bruise
    0.49
     intestines
    0.46
     grooms
    0.46
     deficiency
    0.46
     mutta
    0.45
     satur
    0.45
     sores
    0.44
     crashes
    0.44
    putchar
    0.44
    Activations Density 0.001%

    No Known Activations