© 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. 73830
    Prev
    Next
    INDEX
    Explanations

    legal, awards, and technical terms

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

    discreet luxury. mid-range ejection fraction. previously

    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
    t
    0.50
    0
    0.49
     physician
    0.46
    疾
    0.45
     circol
    0.43
    ত
    0.42
    尽量
    0.41
    XD
    0.41
    ก่
    0.41
     (/
    0.41
    POSITIVE LOGITS
     അമേ
    0.46
    ारण
    0.44
     सदर
    0.44
    affordable
    0.42
     zagro
    0.41
    ርሃ
    0.41
     நம்பிக்கை
    0.41
     출연
    0.41
     empate
    0.41
    рама
    0.40
    Activations Density 0.001%

    No Known Activations