© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 71179
    Prev
    Next
    INDEX
    Explanations

    drivers, range, independence

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

    This solves the key exchange problem

    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
    Negative Logits
     torrent
    0.52
     Orta
    0.49
     あん
    0.46
     Bentham
    0.46
     Kinh
    0.45
     тока
    0.45
     instancias
    0.44
    깐
    0.44
     angust
    0.44
     Lausanne
    0.44
    POSITIVE LOGITS
     triggering
    0.53
    amad
    0.47
    f
    0.47
    ज़्
    0.46
     länger
    0.45
    independence
    0.45
    ahlt
    0.45
    ad
    0.45
     alerting
    0.45
    يل
    0.44
    Activations Density 0.000%

    No Known Activations