© 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. 151418
    Prev
    Next
    INDEX
    Explanations

    cause and condition

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

    directly return

    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
    jami
    0.52
    ong
    0.51
    m
    0.48
    不止
    0.47
    ra
    0.47
     unsafe
    0.47
    vak
    0.46
    j
    0.45
    ibirsk
    0.45
    vil
    0.45
    POSITIVE LOGITS
    ⬯
    0.55
     terminar
    0.50
     pratica
    0.48
    ганда
    0.47
     tagli
    0.47
    썻
    0.46
     しかし
    0.45
     дал
    0.45
     praticamente
    0.45
    জিওথের
    0.45
    Activations Density 0.000%

    No Known Activations