© 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. 130490
    Prev
    Next
    INDEX
    Explanations

    qualification requirements

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

    tomato sauce

    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
     AEW
    0.44
    浥
    0.43
     deacon
    0.42
     sie
    0.42
     Sauer
    0.42
    ies
    0.41
     Inc
    0.41
     kra
    0.41
    myl
    0.41
     AJ
    0.41
    POSITIVE LOGITS
    餞
    0.50
     ошибки
    0.49
    inoceros
    0.46
    䚲
    0.46
     ونص
    0.45
     chahiye
    0.45
    })=\
    0.45
     తెలుగు
    0.44
     ながら
    0.44
    ítása
    0.44
    Activations Density 0.001%

    No Known Activations