© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 6111
    Prev
    Next
    INDEX
    Explanations

    geographic and academic terms

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

    tell jokes or 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
    ਣ
    0.56
    していない
    0.50
     paces
    0.49
    ਾ
    0.48
    ッフ
    0.48
    یسی
    0.48
     límites
    0.47
    ા
    0.47
    ენა
    0.47
     qualité
    0.46
    POSITIVE LOGITS
    Australia
    0.53
     Australia
    0.50
     Maryland
    0.50
     Pakistan
    0.49
     Postgraduate
    0.49
    Pakistan
    0.49
    Austral
    0.48
    sk
    0.48
    Logistic
    0.48
    Neural
    0.47
    Activations Density 0.000%

    No Known Activations