© 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. 195149
    Prev
    Next
    INDEX
    Explanations

    buried in

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

    building dashboards or interfaces

    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
    漱
    0.50
    تان
    0.48
     συγκ
    0.47
    вана
    0.47
    𝚗
    0.47
    ската
    0.46
    тивний
    0.46
    驽
    0.46
    كس
    0.46
    adani
    0.46
    POSITIVE LOGITS
     unchallenged
    0.50
     Admiralty
    0.48
     serine
    0.46
    ン
    0.46
     nonlinear
    0.43
     aryl
    0.42
     pathogenesis
    0.42
     Wrist
    0.42
     vasculature
    0.41
     epoxide
    0.40
    Activations Density 0.002%

    No Known Activations