© 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. 232826
    Prev
    Next
    INDEX
    Explanations

    Object Storage

    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
    کن
    0.53
    كما
    0.50
     ампли
    0.49
    듭
    0.47
     напом
    0.46
     irregularly
    0.45
     கலங்கரை
    0.45
     оптима
    0.45
     እንቅ
    0.45
    パワー
    0.45
    POSITIVE LOGITS
     Pastor
    0.54
     Cinema
    0.48
     Wag
    0.48
     tred
    0.48
     "
    0.47
    äude
    0.47
    ville
    0.46
     Caro
    0.46
    .,
    0.46
    ński
    0.46
    Activations Density 0.000%

    No Known Activations