© 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. 33878
    Prev
    Next
    INDEX
    Explanations

    through or like

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

    confidential information disclosures

    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
    なのです
    0.43
    quette
    0.41
     spécialiste
    0.41
    Ort
    0.40
     policewomen
    0.40
    acée
    0.40
    吕
    0.40
    uche
    0.39
    osof
    0.39
     Maestro
    0.39
    POSITIVE LOGITS
     THROUGH
    0.41
    潑
    0.40
     WASTE
    0.39
     مثل
    0.38
     WHILE
    0.38
    EPEND
    0.37
     LIKE
    0.37
     monopolies
    0.37
    互相
    0.37
     해주
    0.36
    Activations Density 0.002%

    No Known Activations