© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 13064
    Prev
    Next
    INDEX
    Explanations

    failure or absence

    np_acts-logits-general · gemini-2.5-flash-lite

    likely scouting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     यामध्ये
    0.46
     Він
    0.45
     включая
    0.45
    чиго
    0.45
     уйна
    0.45
     ि
    0.44
     중심
    0.43
    瓴
    0.42
    大于
    0.41
     във
    0.41
    POSITIVE LOGITS
     peculiarity
    0.56
     unsuccessful
    0.55
     unsatisfactory
    0.55
    並沒有
    0.53
     unsuitable
    0.52
     peculiarities
    0.52
     peculiar
    0.50
     intended
    0.50
     nevertheless
    0.49
     hardly
    0.49
    Activations Density 0.018%

    No Known Activations