© 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. 111977
    Prev
    Next
    INDEX
    Explanations

    words that relate to quantity or duration

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

    Champs-Élysées and Capitoline Hill

    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
    لع
    0.46
    менту
    0.46
    اند
    0.45
     Hen
    0.43
    وبر
    0.43
    ഌ
    0.43
     Szer
    0.42
    њ
    0.42
    ፅ
    0.42
     edific
    0.42
    POSITIVE LOGITS
     তুলনায়
    0.47
     മേ
    0.47
     (=
    0.45
     লাভ
    0.44
     ,[
    0.43
    ————
    0.42
     letting
    0.41
    水の
    0.41
     formerly
    0.41
     let
    0.41
    Activations Density 0.000%

    No Known Activations