© 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. 91327
    Prev
    Next
    INDEX
    Explanations

    ; then overview

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

    introducing explanation origins

    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
     ی
    0.45
     любом
    0.45
    ủng
    0.44
     مود
    0.44
     یخ
    0.44
     حف
    0.44
     書い
    0.43
     tìm
    0.43
     เศ
    0.43
    MOB
    0.43
    POSITIVE LOGITS
    題
    0.45
     verdad
    0.41
    विक
    0.41
    맏
    0.40
    览
    0.40
     Reel
    0.40
     Roll
    0.39
     Adm
    0.39
    राई
    0.39
    慮
    0.39
    Activations Density 0.000%

    No Known Activations