© 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. 210957
    Prev
    Next
    INDEX
    Explanations

    allow features or improvements

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

    ideas and concepts

    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
    。
    0.50
    ResponseEntity
    0.47
    preprocess
    0.42
    不
    0.41
    。</
    0.41
    gam
    0.40
     glare
    0.40
    ía
    0.39
    隔
    0.39
    ")
    0.39
    POSITIVE LOGITS
     нацыяна
    0.56
    ापुर
    0.50
     мали
    0.48
    поряд
    0.47
    iedy
    0.47
    INY
    0.47
    ники
    0.47
    валися
    0.46
     मुगल
    0.46
     Nascimento
    0.46
    Activations Density 0.000%

    No Known Activations