© 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. 61470
    Prev
    Next
    INDEX
    Explanations

    article or section improvement

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

    fragments of, answer to, Increased Liver

    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
    笾
    0.52
     কোর্স
    0.49
     Wend
    0.44
     GLUT
    0.44
     hilltop
    0.44
     binnen
    0.43
     bermanfaat
    0.43
     статей
    0.42
     paths
    0.42
     Ergebnisse
    0.42
    POSITIVE LOGITS
     refrain
    0.42
     Amérique
    0.41
     rumoured
    0.41
    ","$
    0.40
    should
    0.40
     حكوم
    0.39
    ***",
    0.39
    ☓
    0.39
     spół
    0.39
    sometimes
    0.38
    Activations Density 0.001%

    No Known Activations