© 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. 127241
    Prev
    Next
    INDEX
    Explanations

    mixed language names and titles

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

    formal definition, force, start of turn

    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
     an
    0.53
    0.51
     Lateral
    0.47
     brimming
    0.47
     a
    0.46
     both
    0.46
    i
    0.46
     roughly
    0.46
     Ayurvedic
    0.44
     Reneg
    0.44
    POSITIVE LOGITS
     καθώς
    0.48
     наступ
    0.47
    ዖ
    0.47
    თვის
    0.46
     বলিলাম
    0.46
     தொலை
    0.46
    パターン
    0.45
     contrario
    0.45
     അടിസ്ഥാന
    0.45
    効
    0.44
    Activations Density 0.000%

    No Known Activations