© 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. 45516
    Prev
    Next
    INDEX
    Explanations

    in a

    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
    o
    0.56
    ',
    0.43
     relevant
    0.42
    ai
    0.41
    ...',
    0.40
    *,
    0.40
     considerate
    0.39
     constructors
    0.39
    **,
    0.39
     prochains
    0.39
    POSITIVE LOGITS
     лицен
    0.56
    ມື
    0.50
     இதே
    0.49
    τα
    0.48
    spinal
    0.48
     నే
    0.48
     самого
    0.47
     पृष्ठ
    0.46
     വിദ
    0.46
     η
    0.46
    Activations Density 0.001%

    No Known Activations