© 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. 170046
    Prev
    Next
    INDEX
    Explanations

    method, starboard, storms, number, items, offers

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

    timing of spikes or writing

    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
     የተ
    0.53
    𝓲
    0.52
     فری
    0.48
    𝓗
    0.48
    alamualaikum
    0.48
    𝙽
    0.48
    Cread
    0.48
     বিরাজ
    0.47
    edì
    0.47
     perpetually
    0.47
    POSITIVE LOGITS
     behaviors
    0.49
    v
    0.48
    及
    0.46
    лев
    0.43
     v
    0.42
    вле
    0.41
     han
    0.40
    ле
    0.40
     behaviours
    0.38
     quantile
    0.38
    Activations Density 0.000%

    No Known Activations