© 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. 256373
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    а
    0.53
    （
    0.48
    פו
    0.45
    ３
    0.45
    <0xE7>
    0.45
     ד
    0.43
    ป
    0.42
    פ
    0.42
    <0xE9>
    0.42
    イ
    0.42
    POSITIVE LOGITS
     jeweiligen
    0.50
     jeweil
    0.47
     the
    0.47
     certa
    0.41
     theolog
    0.40
     jeweils
    0.39
     dhamm
    0.39
     qua
    0.39
     perny
    0.39
     zbog
    0.39
    Activations Density 0.002%

    No Known Activations