© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 2610
    Prev
    Next
    INDEX
    Explanations

    verbal pauses & speech

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    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
     menggel
    0.37
    ház
    0.37
    ຈັດ
    0.35
    🩹
    0.35
    }=[
    0.35
    гант
    0.35
    anganan
    0.35
    핌
    0.35
     charset
    0.35
    harmed
    0.34
    POSITIVE LOGITS
     verbal
    1.03
     speaking
    1.02
     utterances
    1.00
     speech
    0.99
     बोलने
    0.95
     speak
    0.94
     Speaking
    0.90
    发言
    0.89
    พูด
    0.89
     말을
    0.89
    Activations Density 0.090%

    No Known Activations