© 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. 69054
    Prev
    Next
    INDEX
    Explanations

    contextual phrase completions

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

    communication status or protocol

    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
     आया
    0.49
     ກ
    0.49
     つ
    0.48
    lerinden
    0.48
     មាន
    0.47
     สาย
    0.47
     ಫ
    0.46
     flung
    0.46
     sputtered
    0.46
     sprayed
    0.45
    POSITIVE LOGITS
    ோர்
    0.53
    رح
    0.49
     innervation
    0.45
    lift
    0.44
    剧
    0.44
    冂
    0.43
    ERA
    0.43
    同一
    0.43
    界
    0.43
    COU
    0.42
    Activations Density 0.000%

    No Known Activations