© 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. 64380
    Prev
    Next
    INDEX
    Explanations

    LED Display

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

    understanding * why

    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
     CIT
    0.52
     Gemini
    0.51
     denying
    0.50
     BLUE
    0.47
     GEM
    0.47
     Jamal
    0.46
     pads
    0.46
    ാ
    0.46
     Fac
    0.44
    t
    0.44
    POSITIVE LOGITS
    sees
    0.51
     између
    0.46
    áles
    0.45
    智能化
    0.45
    ningarna
    0.44
    uretics
    0.44
    érc
    0.44
     ہوج
    0.44
    nerg
    0.43
    Ⲱ
    0.43
    Activations Density 0.000%

    No Known Activations