© 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. 92058
    Prev
    Next
    INDEX
    Explanations

    tone and tons

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

    tone attributes

    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
    ים
    0.53
    ു
    0.49
    BH
    0.48
    ির
    0.47
     Arrange
    0.47
    ни
    0.47
    APA
    0.46
    يء
    0.45
    s
    0.45
    transferase
    0.45
    POSITIVE LOGITS
     tones
    0.89
    Tone
    0.85
     tone
    0.81
     тон
    0.75
     ton
    0.74
     тонн
    0.73
     Tone
    0.73
     toned
    0.71
     tono
    0.71
    톤
    0.71
    Activations Density 0.048%

    No Known Activations