© 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. 433
    Prev
    Next
    INDEX
    Explanations

    metadata and links

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

    explaining and noting details

    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
    ,
    0.22
     to
    0.21
    -
    0.21
    _
    0.20
    ',
    0.20
     glyphicon
    0.20
     chinos
    0.19
     {-
    0.19
     beacons
    0.19
    (:,
    0.19
    POSITIVE LOGITS
    Weblinks
    0.26
    Weitere
    0.25
    Ссылки
    0.23
    Keywords
    0.23
    સ
    0.22
    doi
    0.22
    ભાગ
    0.22
    Permalink
    0.22
    Published
    0.21
    Código
    0.21
    Activations Density 0.320%

    No Known Activations