© 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-65K
    7. 51226
    Prev
    Next
    INDEX
    Explanations

    instructional or procedural steps

    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_65k_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
    ͊
    0.39
     unexpected
    0.39
    abek
    0.38
    kušen
    0.37
    <unused999>
    0.37
    ​​
    0.36
    ahu
    0.36
     menurun
    0.36
    kfollowers
    0.36
    ajima
    0.36
    POSITIVE LOGITS
     базе
    0.47
     erste
    0.47
     Version
    0.42
     graphon
    0.42
    CRUD
    0.42
     f
    0.41
     Erweiter
    0.41
    Rename
    0.41
     விரிவா
    0.41
     Explosion
    0.41
    Activations Density 0.034%

    No Known Activations