© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 51631
    Prev
    Next
    INDEX
    Explanations

    sensors, suspended, found

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    戒指
    0.53
     cabbage
    0.41
    トリ
    0.41
     dwellings
    0.39
     თუ
    0.38
     обязательно
    0.38
     buttons
    0.37
    催
    0.37
     if
    0.37
    пература
    0.37
    POSITIVE LOGITS
    یشنل
    0.47
    bromide
    0.47
    José
    0.46
     Peker
    0.45
    Hun
    0.44
    skcipher
    0.44
    Fork
    0.43
    Dropout
    0.43
     እነ
    0.43
     senador
    0.43
    Activations Density 0.002%

    No Known Activations