© 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. 233337
    Prev
    Next
    INDEX
    Explanations

    modern, contemporary, crafted objects

    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
    ｉ
    0.42
    ᱥ
    0.42
    ο
    0.42
    ａ
    0.42
    、
    0.42
    <0xE3>
    0.41
    书
    0.41
    挀
    0.40
    影响
    0.39
    。。。
    0.39
    POSITIVE LOGITS
     explosives
    0.47
    製の
    0.46
     hordes
    0.46
     versions
    0.46
     weapons
    0.45
     murderers
    0.45
     uprisings
    0.45
     ganger
    0.45
     rifles
    0.44
     murderous
    0.44
    Activations Density 0.016%

    No Known Activations