© 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. 8373
    Prev
    Next
    INDEX
    Explanations

    URLs and foreign language links

    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
     mRNAs
    0.30
     recomb
    0.29
     প্রথমেই
    0.29
     groupes
    0.28
    __:
    0.27
     penetrate
    0.27
     ያሉ
    0.27
     acceptors
    0.27
    患者
    0.27
    ’:
    0.27
    POSITIVE LOGITS
     и
    0.36
    पणे
    0.34
     teşekkür
    0.34
     übrigens
    0.34
     dito
    0.34
    ं
    0.34
     gimana
    0.33
    ore
    0.32
    google
    0.32
     और
    0.32
    Activations Density 0.465%

    No Known Activations