© 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. 90911
    Prev
    Next
    INDEX
    Explanations

    single File

    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
    ค์
    0.48
     Tristan
    0.47
    UNT
    0.45
    ༦
    0.45
    Editors
    0.45
     edi
    0.45
     usa
    0.45
    羲
    0.44
    rome
    0.44
     Gossip
    0.44
    POSITIVE LOGITS
     большей
    0.46
     possessions
    0.45
    ي
    0.45
    ieuse
    0.42
     drained
    0.42
     pouring
    0.41
    رش
    0.41
     preserved
    0.41
     drenched
    0.41
    ią
    0.40
    Activations Density 0.000%

    No Known Activations