© 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. 193273
    Prev
    Next
    INDEX
    Explanations

    voice and speech

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

    Okay Google

    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
     ликви
    0.56
    ophthal
    0.47
     CELLS
    0.45
     UIScrollView
    0.45
     toep
    0.43
     Linkedin
    0.42
     VEH
    0.41
    篩
    0.41
    amis
    0.40
    械
    0.40
    POSITIVE LOGITS
     conversational
    0.71
    音声
    0.67
     speech
    0.67
    语音
    0.66
     voice
    0.64
     Speech
    0.63
    音频
    0.62
    Speech
    0.62
     utterances
    0.62
     utterance
    0.60
    Activations Density 0.081%

    No Known Activations