© 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-65K
    7. 52754
    Prev
    Next
    INDEX
    Explanations

    peaks and maxima

    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_65k_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
    வைத்த
    0.40
    Pitch
    0.40
    вай
    0.39
    速
    0.39
    ⏩
    0.39
    揮
    0.38
    醎
    0.38
    ॉजी
    0.38
    lossen
    0.38
    Rate
    0.37
    POSITIVE LOGITS
     peaks
    1.49
     Peaks
    1.28
    peaks
    1.23
     peak
    1.23
    Peaks
    1.13
     Peak
    1.08
    Peak
    1.03
    peak
    1.01
    峰
    0.99
    ピーク
    0.98
    Activations Density 0.057%

    No Known Activations