© 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. 112839
    Prev
    Next
    INDEX
    Explanations

    rental, geological, material, health, procedures

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

    examples, discussions, and points

    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
     rendelkez
    0.52
     indications
    0.49
     Türk
    0.48
    lenen
    0.48
    ى
    0.46
     anlamına
    0.46
    蹋
    0.46
     beraber
    0.45
    تبر
    0.44
     amounting
    0.44
    POSITIVE LOGITS
    U
    0.47
    Rc
    0.45
    Cn
    0.45
    QCD
    0.44
    Sebelum
    0.44
     भले
    0.43
    Dichloro
    0.43
    Ij
    0.43
    Discussion
    0.42
    1
    0.42
    Activations Density 0.004%

    No Known Activations