© 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. 173435
    Prev
    Next
    INDEX
    Explanations

    spoken or written descriptions

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

    relevant policy solutions

    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
    迪士
    0.53
    注意事項
    0.49
     stora
    0.49
    ر
    0.49
    OS
    0.48
     kk
    0.48
    ratio
    0.47
    𝗁
    0.46
     informasjon
    0.46
    मा
    0.46
    POSITIVE LOGITS
    asthenia
    0.47
     unidirectional
    0.47
    otoxin
    0.46
     articulate
    0.46
    unctional
    0.45
    artic
    0.44
    ético
    0.43
    otopy
    0.43
    imental
    0.42
     articulated
    0.42
    Activations Density 0.003%

    No Known Activations