© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 3577
    Prev
    Next
    INDEX
    Explanations

    video resolutions and years

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

    numbers and durations

    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_53_width_65k_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
     trăm
    0.41
    百万
    0.40
    𓈒
    0.38
    牪
    0.38
     বিভ
    0.38
    ी
    0.37
    više
    0.37
    拭
    0.37
    ið
    0.36
    ে
    0.36
    POSITIVE LOGITS
    th
    0.66
    वीं
    0.56
    ″
    0.54
     वीं
    0.53
     Downing
    0.51
     Commandments
    0.50
     మంది
    0.49
    ′
    0.47
    yrs
    0.45
     lutego
    0.45
    Activations Density 0.342%

    No Known Activations