© 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. 31313
    Prev
    Next
    INDEX
    Explanations

    dates and specific items

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

    brokenCalc, while oftenirrelevant

    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
     Oracle
    0.52
     आरामदायक
    0.51
    狷
    0.50
     Tox
    0.48
     N
    0.47
     S
    0.47
     Xu
    0.46
     Akadem
    0.46
     Lin
    0.46
     Poems
    0.45
    POSITIVE LOGITS
    =",
    0.47
     bluntly
    0.46
    بوت
    0.45
     pulsating
    0.44
    ᱔
    0.44
    ()"
    0.44
     नवा
    0.44
     قي
    0.43
     choppy
    0.43
     sheared
    0.43
    Activations Density 0.000%

    No Known Activations