© 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. 208157
    Prev
    Next
    INDEX
    Explanations

    type context

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

    causes exceptions

    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
    న్నారు
    0.51
     количе
    0.48
    Enumerator
    0.46
    Comparing
    0.46
    지만
    0.45
    ющей
    0.45
     एनी
    0.45
    ]");
    0.44
     договора
    0.44
    Enumer
    0.44
    POSITIVE LOGITS
     terapia
    0.53
     brukes
    0.51
     medicina
    0.46
     duro
    0.46
     funktion
    0.45
     funktioniert
    0.45
     type
    0.45
     tipo
    0.44
     permanente
    0.44
     terapi
    0.44
    Activations Density 0.000%

    No Known Activations