© 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. 222601
    Prev
    Next
    INDEX
    Explanations

    "'omitted explanations' or descriptions

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

    language, not perfection

    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
    decreasing
    0.44
     landfills
    0.42
    ತ್
    0.40
    विध
    0.40
    圧
    0.40
    trumpet
    0.40
    પ્ત
    0.40
     seizure
    0.40
     rinsing
    0.39
    retirement
    0.39
    POSITIVE LOGITS
    ">'
    0.55
    orElse
    0.52
     vieron
    0.52
     pierws
    0.50
     unknown
    0.49
     mensal
    0.49
     о
    0.48
     rek
    0.48
     adaptador
    0.48
     yoj
    0.47
    Activations Density 0.001%

    No Known Activations