© 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. 381
    Prev
    Next
    INDEX
    Explanations

    your own data

    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
    以
    0.20
    </td>
    0.20
     accede
    0.19
     characterise
    0.19
     etiam
    0.19
    有不少
    0.19
     becom
    0.19
     (|
    0.18
     нередко
    0.18
     («
    0.18
    POSITIVE LOGITS
     own
    0.42
     beloved
    0.40
     favorite
    0.38
     entire
    0.37
     kiddos
    0.36
     favourite
    0.32
     lovely
    0.30
     newfound
    0.29
     precious
    0.29
     biggest
    0.29
    Activations Density 1.404%

    No Known Activations