© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 77511
    Prev
    Next
    INDEX
    Explanations

    emotional expressions after emphasis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Hepin
    0.35
    //
    0.34
    हमने
    0.34
    䀨
    0.32
    *((*
    0.32
    ivesse
    0.31
    比利
    0.31
     بیل
    0.31
    []);
    0.31
     Vell
    0.30
    POSITIVE LOGITS
     бывают
    0.34
     conclusions
    0.31
     आकर
    0.31
     anyway
    0.30
    λει
    0.29
    섹
    0.29
     Are
    0.29
    ukul
    0.29
    沆
    0.29
     lakini
    0.29
    Activations Density 0.001%

    No Known Activations