© 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. 219642
    Prev
    Next
    INDEX
    Explanations

    dates and events

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

    describing voice quality

    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
    t
    0.59
     hsl
    0.49
    q
    0.49
    ంబేద్కర్
    0.48
    asts
    0.47
     únicas
    0.47
    т
    0.46
     –
    0.46
     emotes
    0.46
    𝒕
    0.46
    POSITIVE LOGITS
     rethinking
    0.49
     ชีวิต
    0.48
     reconsideration
    0.47
     THAT
    0.46
     deregulation
    0.46
    決
    0.45
    vē
    0.45
    estimation
    0.44
     supplément
    0.44
    uleux
    0.43
    Activations Density 0.001%

    No Known Activations