© 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. 250655
    Prev
    Next
    INDEX
    Explanations

    scholarship funds and daughter stories

    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
    ch
    0.54
    s
    0.53
    DoesNotExist
    0.51
     sollte
    0.51
    fraud
    0.51
     সুখী
    0.49
     ഇല്ല
    0.49
    ไม่ใช่
    0.49
     ؛
    0.49
    ChangeString
    0.49
    POSITIVE LOGITS
     álbum
    0.52
     académico
    0.50
     estaciones
    0.48
     parenteral
    0.48
    ế
    0.46
     peserta
    0.45
     desktop
    0.44
     investigator
    0.43
    iente
    0.41
     tera
    0.41
    Activations Density 0.001%

    No Known Activations