© 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. 185264
    Prev
    Next
    INDEX
    Explanations

    afterwards, between, greatest, photos

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

    Explaining conditions and consequences

    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
    ophagus
    0.49
     रिश्ते
    0.47
     posit
    0.46
    tte
    0.46
    curricular
    0.46
     kwiet
    0.44
     Serpent
    0.44
    oches
    0.43
    ?
    0.43
     Kensington
    0.43
    POSITIVE LOGITS
     systemu
    0.48
    ivé
    0.47
    Trước
    0.47
     systému
    0.45
    Pokud
    0.45
    ፊት
    0.45
     '*')
    0.45
     সিস্টেম
    0.44
    Tous
    0.43
     fournisseur
    0.43
    Activations Density 0.001%

    No Known Activations