© 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. 66652
    Prev
    Next
    INDEX
    Explanations

    watched each other

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

    ability to

    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
     ลักษณะ
    0.51
     рівня
    0.47
    s
    0.47
     而
    0.46
     但是
    0.45
    asible
    0.44
     தயாரிக்க
    0.44
    anie
    0.43
     অন্যদিকে
    0.42
     Reid
    0.42
    POSITIVE LOGITS
    ປັນ
    0.44
    makeText
    0.43
    ће
    0.42
    mical
    0.42
     activa
    0.42
    тих
    0.41
     specular
    0.41
     svc
    0.41
    嘴
    0.41
     sóc
    0.40
    Activations Density 0.001%

    No Known Activations