© 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. 225383
    Prev
    Next
    INDEX
    Explanations

    believe me

    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
    앜
    0.47
     でき
    0.46
    alkyl
    0.43
     proyek
    0.43
    槸
    0.42
    です
    0.41
    ูก
    0.41
     डिवीजन
    0.41
     العدد
    0.41
    ıyorum
    0.41
    POSITIVE LOGITS
    rit
    0.51
     sogenannten
    0.47
    joen
    0.47
    riss
    0.47
    lo
    0.42
     Lehr
    0.42
    ጩ
    0.41
    rss
    0.41
    png
    0.40
     eje
    0.40
    Activations Density 0.001%

    No Known Activations