© 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. 41097
    Prev
    Next
    INDEX
    Explanations

    proportion or quantity

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

    pre-world historical periods

    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
    济
    0.51
     እንደሚ
    0.41
     যা
    0.40
    OfThe
    0.40
    PropertyParam
    0.40
    AuditEvent
    0.39
    ή
    0.38
    াই
    0.38
    ומי
    0.38
    ক্টর
    0.38
    POSITIVE LOGITS
     meio
    0.54
     मिड
    0.49
     relativement
    0.48
    seits
    0.48
     méthodique
    0.48
     sisält
    0.48
     midrange
    0.47
     contient
    0.47
     mids
    0.46
     moi
    0.45
    Activations Density 0.000%

    No Known Activations