© 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. 196119
    Prev
    Next
    INDEX
    Explanations

    questions about your own dataset

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

    finding and contacting prospects

    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
    打造
    0.54
    你知道
    0.46
    PE
    0.46
    ERI
    0.46
    Core
    0.44
    滨
    0.44
    Inc
    0.44
    讓
    0.44
    AGA
    0.44
     FLOOR
    0.44
    POSITIVE LOGITS
    n
    0.58
    sts
    0.56
    q
    0.53
    т
    0.51
    ammlung
    0.51
    tts
    0.49
    satz
    0.48
    t
    0.48
    irond
    0.47
    mss
    0.47
    Activations Density 0.000%

    No Known Activations