© 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. 195553
    Prev
    Next
    INDEX
    Explanations

    local places and events

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

    conditions or consciousness

    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
    р
    0.57
    ν
    0.47
     ঔ
    0.44
     Klasse
    0.43
     PHY
    0.42
    ኖ
    0.41
    м
    0.41
    з
    0.41
    扃
    0.40
    к
    0.40
    POSITIVE LOGITS
     convicts
    0.53
    нением
    0.51
     zašt
    0.47
    blem
    0.46
     स्वरूप
    0.46
     حساب
    0.46
    AFTER
    0.45
     indik
    0.45
    чему
    0.45
     तेंदुआ
    0.45
    Activations Density 0.001%

    No Known Activations