© 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. 60318
    Prev
    Next
    INDEX
    Explanations

    numbers and special words

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

    peace and charity

    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
    ERA
    0.55
    Е
    0.52
    証
    0.51
    DA
    0.48
    B
    0.48
    利
    0.47
     changer
    0.46
     меня
    0.46
    RI
    0.46
    X
    0.46
    POSITIVE LOGITS
     accanto
    0.51
     unpleasant
    0.48
     navegar
    0.45
    deload
    0.45
    solvent
    0.45
     enfrentar
    0.44
     astfel
    0.44
     naast
    0.43
     engulf
    0.43
    cartes
    0.43
    Activations Density 0.001%

    No Known Activations