© 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. 5767
    Prev
    Next
    INDEX
    Explanations

    voice, vocal, singing, pitch

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

    voice accent pronunciation

    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
     финанси
    0.56
    economic
    0.54
     economic
    0.54
    LOY
    0.49
     financing
    0.49
    debt
    0.48
    轂
    0.48
    TAX
    0.48
    SERVICE
    0.48
    螂
    0.48
    POSITIVE LOGITS
     voice
    1.20
     Voice
    1.20
     vocal
    1.20
     Vocal
    1.16
     giọng
    1.16
    Voice
    1.11
     vocals
    1.09
     voix
    1.07
    语音
    1.04
    嗓
    1.04
    Activations Density 0.080%

    No Known Activations