© 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. 145223
    Prev
    Next
    INDEX
    Explanations

    replacement therapy, stretched perpendicularly, realized there

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

    specific items and concepts

    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
    𝓌
    0.54
    𝒹
    0.51
    𝓀
    0.50
     ξεκ
    0.50
    后端
    0.49
    ستی
    0.49
    𝓈
    0.49
    𝒸
    0.49
    𝓪
    0.46
    άρ
    0.46
    POSITIVE LOGITS
    ↵
    0.52
     monoton
    0.47
     pagal
    0.46
     melted
    0.45
     malam
    0.44
     தெய்வ
    0.42
    VERBOSE
    0.42
    中古
    0.42
     berkom
    0.41
     MIND
    0.41
    Activations Density 0.002%

    No Known Activations