© 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. 7774
    Prev
    Next
    INDEX
    Explanations

    color ingredients and versions

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

    matter type, operations

    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
    ప్ప
    0.36
    籬
    0.34
    انه
    0.33
    ამე
    0.33
    antz
    0.32
    Ⲣ
    0.32
    湎
    0.32
    Ꮓ
    0.32
    KH
    0.31
    سته
    0.31
    POSITIVE LOGITS
     j
    0.35
     ic
    0.35
     tracking
    0.34
     markings
    0.34
     wedding
    0.34
     style
    0.33
     media
    0.33
     remix
    0.32
     Sep
    0.32
    민국
    0.32
    Activations Density 0.038%

    No Known Activations