© 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. 110379
    Prev
    Next
    INDEX
    Explanations

    Related Posts

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

    integrates many, emerged around, combines, strawberries, both Meta

    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
    athers
    0.46
    یدر
    0.41
     qua
    0.41
    ;
    0.40
     focus
    0.40
     punt
    0.40
     রাজনীতি
    0.40
     ime
    0.40
     abd
    0.39
     jeu
    0.39
    POSITIVE LOGITS
     архівної
    0.51
     മേഖ
    0.47
     архі
    0.46
    原来的
    0.46
    書の
    0.46
     OutputStream
    0.44
    ونية
    0.44
    ଠ
    0.44
     حكم
    0.43
    薑
    0.42
    Activations Density 0.000%

    No Known Activations