© 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. 234173
    Prev
    Next
    INDEX
    Explanations

    specific measurements

    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
     aqueles
    0.52
    ка
    0.51
     wine
    0.51
     aquellos
    0.51
    2
    0.50
    wine
    0.48
    那
    0.48
     aquelas
    0.48
    あの
    0.47
    я
    0.47
    POSITIVE LOGITS
     कप्तान
    0.51
    ☬
    0.50
    Deployment
    0.49
    嬋
    0.47
    巉
    0.45
    Deploy
    0.44
    Dial
    0.44
    र्स
    0.44
    Tonel
    0.44
    Bild
    0.43
    Activations Density 0.000%

    No Known Activations