© 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. 51991
    Prev
    Next
    INDEX
    Explanations

    linked list

    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
    б
    0.46
    Beauty
    0.44
    VersionUID
    0.44
    евского
    0.43
    Brown
    0.43
    ॉड
    0.42
    Fitz
    0.42
    га
    0.41
    дор
    0.41
    В
    0.41
    POSITIVE LOGITS
     ball
    0.47
     passiert
    0.46
     Cerebral
    0.46
     Architecture
    0.46
     detained
    0.45
     Ball
    0.45
     अवैध
    0.45
     dort
    0.45
    पालन
    0.44
     engl
    0.44
    Activations Density 0.001%

    No Known Activations