© 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. 42650
    Prev
    Next
    INDEX
    Explanations

    most of

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

    comfortable condition

    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
    斯
    0.53
    Cele
    0.50
    人々
    0.49
     Boul
    0.48
    国の
    0.47
    ニコ
    0.47
    혼
    0.46
    ロボ
    0.46
     soude
    0.46
     Cele
    0.46
    POSITIVE LOGITS
    stead
    0.47
    multif
    0.47
    <unused221>
    0.46
     გან
    0.45
    oid
    0.45
    infiltration
    0.45
    <unused2168>
    0.44
     twin
    0.44
     వివర
    0.44
    multilayer
    0.43
    Activations Density 0.000%

    No Known Activations