© 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. 115117
    Prev
    Next
    INDEX
    Explanations

    quotes and conferences

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

    describing concepts or actions

    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
    是一种
    0.53
    腮
    0.47
    (&(*
    0.46
    troops
    0.46
    过程
    0.45
     原因
    0.45
     Yourself
    0.44
    原因
    0.44
    p
    0.43
    是一種
    0.43
    POSITIVE LOGITS
     casas
    0.49
     harvester
    0.48
    kowitz
    0.46
     silhouette
    0.46
     puente
    0.46
     specialty
    0.45
     hooded
    0.45
     sole
    0.45
     hw
    0.45
    FRAMERATE
    0.45
    Activations Density 0.001%

    No Known Activations