© 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. 91191
    Prev
    Next
    INDEX
    Explanations

    ChatALL

    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
     entangled
    0.51
    幟
    0.47
     outraged
    0.44
    孃
    0.44
    給
    0.43
     across
    0.42
    iostream
    0.41
    បន្ថែម
    0.41
     kilograms
    0.40
     threx
    0.40
    POSITIVE LOGITS
     sefer
    0.52
    ller
    0.46
     reunir
    0.46
    Regulation
    0.44
    р
    0.44
    रल
    0.42
    ર
    0.42
     rép
    0.42
    pper
    0.42
    ر
    0.42
    Activations Density 0.010%

    No Known Activations