© 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. 136223
    Prev
    Next
    INDEX
    Explanations

    collaboration opportunity, development after

    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
     book
    0.49
     adjective
    0.49
     a
    0.48
     be
    0.45
     forme
    0.45
     create
    0.44
     an
    0.44
     sentient
    0.43
     smoky
    0.43
     tuoi
    0.43
    POSITIVE LOGITS
    ^{\#}\
    0.51
    嘱
    0.50
     alınan
    0.48
    ÈRE
    0.48
     Между
    0.48
     Altogether
    0.47
     җиңү
    0.46
    ál
    0.46
     التح
    0.46
    өлү
    0.46
    Activations Density 0.001%

    No Known Activations