© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48514
    Prev
    Next
    INDEX
    Explanations

    names of athletes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    踔
    -0.88
     fennel
    -0.82
    adoles
    -0.81
    𝖛
    -0.80
     trocar
    -0.80
     ulcers
    -0.79
     Enkel
    -0.79
     deriva
    -0.76
    satisfaction
    -0.76
    álat
    -0.76
    POSITIVE LOGITS
     क्योंकि
    0.82
    Mania
    0.82
     Hert
    0.81
    |}{\
    0.79
    Happ
    0.76
    depth
    0.75
     دید
    0.75
    SZ
    0.75
     consideró
    0.75
    Stud
    0.75
    Activations Density 0.066%

    No Known Activations