© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 109178
    Prev
    Next
    INDEX
    Explanations

    titles and names

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

    dry leaves skittering

    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_31_width_262k_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
    termilk
    0.47
    या
    0.45
    だけの
    0.44
    ਬਰ
    0.44
    ibly
    0.42
    .
    0.42
    出す
    0.42
    textbackslash
    0.41
     infiltrate
    0.41
    말
    0.41
    POSITIVE LOGITS
    )</
    0.58
     Jacobs
    0.57
     Huan
    0.57
    )-\
    0.56
     Padilla
    0.54
     Đế
    0.54
     Sơn
    0.53
     Lambert
    0.52
     Lecturer
    0.52
     Carmen
    0.52
    Activations Density 0.000%

    No Known Activations