© 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. 86299
    Prev
    Next
    INDEX
    Explanations

    CMS, Paris, outputs, surprising

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

    if you

    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
     also
    0.53
     and
    0.49
     leverages
    0.49
    Q
    0.48
    q
    0.46
    AP
    0.46
    Z
    0.45
    (
    0.44
    е
    0.44
    ର୍
    0.43
    POSITIVE LOGITS
     anarchy
    0.54
     offenbar
    0.49
    knię
    0.49
     싫
    0.48
     fierc
    0.48
     실패
    0.47
     Anakin
    0.47
     गड़ब
    0.45
     अपमान
    0.45
    mniejs
    0.45
    Activations Density 0.001%

    No Known Activations