© 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-262K
    7. 90786
    Prev
    Next
    INDEX
    Explanations

    values after certain words

    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_262k_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
    ERTY
    0.46
    +:
    0.46
    goed
    0.45
    _+
    0.44
     kubwa
    0.43
     вас
    0.43
    मेरे
    0.43
     ଆ
    0.43
     minha
    0.42
     employers
    0.42
    POSITIVE LOGITS
    ými
    0.44
     classic
    0.41
    brush
    0.39
    กับการ
    0.39
    dw
    0.38
    3
    0.38
    ेंगी
    0.37
    しろ
    0.36
    4
    0.36
     प्रमुख
    0.36
    Activations Density 0.005%

    No Known Activations