© 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. 59696
    Prev
    Next
    INDEX
    Explanations

    matching sans, embedded pet

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

    business without, spans, cue

    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
     литературы
    0.45
    速度
    0.45
     молоде
    0.45
     истины
    0.44
    答
    0.43
     альтерна
    0.43
     скорость
    0.42
    自分が
    0.42
    ร้อม
    0.42
    芗
    0.42
    POSITIVE LOGITS
    ्ले
    0.49
    geojson
    0.48
    میم
    0.47
     ubiquitin
    0.46
     charted
    0.45
     ellipso
    0.45
     bromine
    0.43
     neoprene
    0.43
     फाइनेंशियल
    0.42
     chemokine
    0.42
    Activations Density 0.000%

    No Known Activations