© 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. 80958
    Prev
    Next
    INDEX
    Explanations

    options: EPUB, SETUP, BUFFER

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

    configuration options and properties

    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
    珩
    0.41
     dosta
    0.39
     କରି
    0.39
     শুরু
    0.38
    決
    0.38
     पिता
    0.38
     én
    0.38
     മൂ
    0.38
     مام
    0.38
     municip
    0.38
    POSITIVE LOGITS
     {};
    0.44
     averages
    0.42
    Segment
    0.42
     Segment
    0.41
     fussy
    0.41
     disk
    0.41
     notch
    0.40
     lemon
    0.39
     Attractive
    0.39
    ರಳ
    0.39
    Activations Density 0.000%

    No Known Activations