© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 3793
    Prev
    Next
    INDEX
    Explanations

    hyphenated word sequences

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

    list item separators: * , :

    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
    の中でも
    0.45
    habilitation
    0.44
     hematopoietic
    0.39
     "~/
    0.38
    ங்களின்
    0.38
     సంబంధించిన
    0.38
    ब्बत
    0.38
     dolomite
    0.37
    ಿಯ
    0.37
    disposing
    0.37
    POSITIVE LOGITS
    &-
    0.68
    year
    0.57
    of
    0.53
    day
    0.51
    and
    0.51
    ever
    0.50
    to
    0.50
    in
    0.48
    sized
    0.48
    by
    0.46
    Activations Density 0.174%

    No Known Activations