© 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. 98880
    Prev
    Next
    INDEX
    Explanations

    organic media, small projects, previous big

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

    professional creative tasks

    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
    嵌
    0.50
    CRYPT
    0.49
    EDED
    0.49
    EXECUT
    0.48
    ==========
    0.47
    eded
    0.47
    TOKEN
    0.46
    TER
    0.46
    ETT
    0.45
    executable
    0.45
    POSITIVE LOGITS
    porters
    0.45
    猬
    0.44
     हेल्पलाइन
    0.44
     checkout
    0.43
     handcuffs
    0.43
     certificat
    0.42
     सॉफ्टवेयर
    0.42
    ේ
    0.41
    ྥ
    0.41
     blogs
    0.41
    Activations Density 0.001%

    No Known Activations