© 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. 134970
    Prev
    Next
    INDEX
    Explanations

    time and computational context

    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
     Example
    0.48
     EXAMPLE
    0.48
     হয়নি
    0.45
    -
    0.45
    вані
    0.43
    ට
    0.42
    ⌣
    0.41
    镜头
    0.41
    ী
    0.41
    ंट
    0.40
    POSITIVE LOGITS
     نها
    0.56
     فر
    0.49
     ער
    0.48
     سنت
    0.47
     traversing
    0.46
     المره
    0.46
    fetchone
    0.44
     vych
    0.43
    meer
    0.42
     سنة
    0.42
    Activations Density 0.000%

    No Known Activations