© 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. 37733
    Prev
    Next
    INDEX
    Explanations

    sewn up, RPG maker, hypnosis training

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

    complex situation

    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
     path
    0.53
    ي
    0.51
    out
    0.50
     pipes
    0.50
     want
    0.49
     management
    0.47
    i
    0.47
     courageous
    0.47
     philosoph
    0.46
     workout
    0.46
    POSITIVE LOGITS
    𝙏
    0.54
     LUMPUR
    0.52
    𝗣
    0.52
    ওয়ে
    0.51
    ত্রের
    0.51
    कॉइन
    0.51
    apabb
    0.50
    缀
    0.49
     hạng
    0.48
    cadastro
    0.48
    Activations Density 0.000%

    No Known Activations