© 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. 158250
    Prev
    Next
    INDEX
    Explanations

    immortality hours

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

    legal principles, runtime permission

    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
     waveguides
    0.51
     criticized
    0.49
    ቓ
    0.47
    ковий
    0.47
    慑
    0.47
    ърква
    0.46
     ionization
    0.45
    мулятор
    0.45
    ारीरिक
    0.44
     ہوئی
    0.44
    POSITIVE LOGITS
    X
    0.61
    1
    0.59
    I
    0.53
    piece
    0.52
    R
    0.52
    Ex
    0.52
    half
    0.52
     Excellency
    0.51
    DEA
    0.51
    =(
    0.51
    Activations Density 0.000%

    No Known Activations