© 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. 154927
    Prev
    Next
    INDEX
    Explanations

    media and viral content

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

    benefit, money, vowel, detector

    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
     গণহত্যার
    0.54
    ferenz
    0.53
    絲
    0.50
     وارد
    0.49
    至于
    0.49
    كال
    0.48
    龅
    0.47
    FOR
    0.47
    Modular
    0.47
    vertret
    0.47
    POSITIVE LOGITS
     sign
    0.54
     free
    0.54
     take
    0.53
     track
    0.52
    णु
    0.52
     lat
    0.51
     gage
    0.51
     a
    0.50
     meas
    0.50
     strategy
    0.50
    Activations Density 0.001%

    No Known Activations