© 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. 195349
    Prev
    Next
    INDEX
    Explanations

    titles, specific reservations, or presidents

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

    distribution of resources

    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
    OTTOM
    0.42
     trazendo
    0.42
    i
    0.42
     hormon
    0.41
     Horm
    0.41
     мала
    0.41
     ตอบ
    0.40
    Checking
    0.40
     bouch
    0.40
    ofType
    0.40
    POSITIVE LOGITS
     árv
    0.43
    树
    0.43
    应急
    0.42
    灰
    0.42
    區
    0.42
    总统
    0.41
     drzew
    0.41
    ۈ
    0.41
     காட்டு
    0.40
     প্রেসিডেন্টের
    0.40
    Activations Density 0.000%

    No Known Activations