© 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. 172172
    Prev
    Next
    INDEX
    Explanations

    Pakistan Academy

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

    speaks in riddles or sentences

    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
     hinsichtlich
    0.45
    ids
    0.44
    uer
    0.42
     (...
    0.42
     сад
    0.41
    property
    0.41
    }$$
    0.40
    ayit
    0.40
     agradecer
    0.40
     monetize
    0.40
    POSITIVE LOGITS
    때
    0.48
    בות
    0.47
    ্যেষ্ঠ
    0.47
     FRE
    0.46
    ছেন
    0.46
    ሠራ
    0.46
     immunos
    0.45
     లు
    0.44
    इकिल
    0.44
    ‍या
    0.44
    Activations Density 0.001%

    No Known Activations