© 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. 6561
    Prev
    Next
    INDEX
    Explanations

    calendar days, law offices, excel files

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

    lists followed by etc

    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
    ారి
    0.42
     vyp
    0.42
     ",
    0.40
    रियर
    0.40
     ","
    0.39
     backtrack
    0.39
     ない
    0.39
    寘
    0.39
    ృత
    0.38
    費用
    0.38
    POSITIVE LOGITS
     Redistributions
    0.48
    bleeds
    0.46
     flags
    0.44
    genres
    0.43
    mentare
    0.42
    flags
    0.42
    spots
    0.42
    Flags
    0.41
    books
    0.41
    owels
    0.41
    Activations Density 0.004%

    No Known Activations