© 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. 246291
    Prev
    Next
    INDEX
    Explanations

    site.reserved.calls.one can.network.Inc

    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
    етки
    0.49
     Mari
    0.46
    詹
    0.45
     журнал
    0.44
    瞟
    0.44
    Jorge
    0.44
     чтения
    0.44
    雎
    0.44
    KA
    0.43
    இதனால்
    0.43
    POSITIVE LOGITS
     usado
    0.49
    ldes
    0.47
    destino
    0.47
     whose
    0.46
     است
    0.45
     principe
    0.44
    caso
    0.44
     incurred
    0.44
     patr
    0.44
    mos
    0.44
    Activations Density 0.001%

    No Known Activations