© 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. 134139
    Prev
    Next
    INDEX
    Explanations

    file downloads or series mentions

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

    false, no, questions, measure, converting

    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
    television
    0.47
    medical
    0.47
    learning
    0.46
    bathtub
    0.43
    বাগ
    0.42
    apprentissage
    0.42
    _
    0.42
    description
    0.41
    Reading
    0.41
    task
    0.41
    POSITIVE LOGITS
     ဒ
    0.50
    д
    0.50
     ولی
    0.50
     خصوصی
    0.49
     ولي
    0.48
     छत्तीस
    0.47
     bond
    0.47
    钞
    0.47
     Ali
    0.47
     Sabah
    0.47
    Activations Density 0.000%

    No Known Activations