© 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. 127043
    Prev
    Next
    INDEX
    Explanations

    year, number, or certain

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

    finding passwords or typical cases

    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
     marad
    0.64
     bad
    0.47
     кому
    0.47
     spree
    0.47
     zvlá
    0.47
    >∕</
    0.47
     clever
    0.46
     revolution
    0.46
     hydroly
    0.46
    ikker
    0.45
    POSITIVE LOGITS
     Populations
    0.49
    ５
    0.48
    データを
    0.47
    اشة
    0.47
     বৎসর
    0.46
    線を
    0.46
    বছর
    0.46
    कर
    0.45
    kfollowers
    0.45
    columns
    0.45
    Activations Density 0.001%

    No Known Activations