© 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. 149065
    Prev
    Next
    INDEX
    Explanations

    Purdue Pharma season frames mung heat

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

    descriptions of things

    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
     boh
    0.48
     caregiver
    0.47
     lawmaker
    0.46
     seh
    0.46
     pengguna
    0.46
    ടുന്ന
    0.46
    अधिक
    0.45
    ’
    0.45
     perencanaan
    0.44
    angaroo
    0.44
    POSITIVE LOGITS
    ración
    0.54
    ]}(
    0.51
    و
    0.50
    플레이
    0.48
    lidir
    0.47
     ሥራ
    0.47
     mannit
    0.46
     آتی
    0.46
     ناول
    0.46
     mixts
    0.46
    Activations Density 0.000%

    No Known Activations