© 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. 50478
    Prev
    Next
    INDEX
    Explanations

    featured in, similar designs

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

    evolving consciousness

    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
    "."
    0.46
    :
    0.44
     церков
    0.44
     intercourse
    0.44
     cellpadding
    0.44
    garten
    0.43
    maxx
    0.43
     operative
    0.43
    Their
    0.42
     Röntgen
    0.42
    POSITIVE LOGITS
    యన్స్
    0.48
    ভাগ
    0.46
    وى
    0.45
     నమో
    0.45
    䙲
    0.44
    上方
    0.43
    設定
    0.43
     localização
    0.43
     busc
    0.42
     Comunidad
    0.42
    Activations Density 0.000%

    No Known Activations