© 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. 106888
    Prev
    Next
    INDEX
    Explanations

    except

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

    contrasting conjunctions and exceptions

    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
    ުރު
    0.43
     問
    0.42
     ৩৬
    0.41
    ଥ
    0.41
     黃
    0.41
     המס
    0.41
    有點
    0.40
     tương
    0.40
    selling
    0.39
     Tosc
    0.39
    POSITIVE LOGITS
     kecuali
    0.46
    Except
    0.45
     Except
    0.44
    O
    0.43
    Unary
    0.43
    eded
    0.43
     except
    0.41
     wanting
    0.41
     Dots
    0.41
    imiz
    0.41
    Activations Density 0.001%

    No Known Activations