© 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. 110376
    Prev
    Next
    INDEX
    Explanations

    biological and relational concepts

    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
     fwrite
    0.43
     sunscreen
    0.42
    博客
    0.42
     enquiry
    0.40
     garantizar
    0.40
     kekuatan
    0.39
    yld
    0.39
     쭉
    0.39
    Qual
    0.39
    粡
    0.39
    POSITIVE LOGITS
     burb
    0.45
    /+
    0.44
     पड़ती
    0.43
     мили
    0.43
     μετά
    0.42
    MatContext
    0.41
    AndPassword
    0.40
     переход
    0.40
     Cupid
    0.40
     confuses
    0.40
    Activations Density 0.008%

    No Known Activations