© 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. 55275
    Prev
    Next
    INDEX
    Explanations

    past events and timeframes

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

    past performance is not indicative of future results

    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
    р
    0.74
    ла
    0.65
     În
    0.65
    প্রকার
    0.64
    𝚖
    0.63
     فِي
    0.62
     металла
    0.62
    大的
    0.62
     Analyse
    0.61
     stvar
    0.61
    POSITIVE LOGITS
    s
    1.73
     past
    1.12
    past
    1.00
    ਆਂ
    0.90
     अतीत
    0.90
    Past
    0.88
     vergang
    0.87
    ের
    0.85
    ים
    0.85
    를
    0.84
    Activations Density 0.021%

    No Known Activations