© 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. 40808
    Prev
    Next
    INDEX
    Explanations

    application server instance

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

    rotation

    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
    VAE
    0.46
    Houses
    0.41
    屐
    0.41
    VE
    0.40
    TP
    0.39
    aklar
    0.39
    den
    0.38
    SPA
    0.38
     武
    0.38
     Antibodies
    0.38
    POSITIVE LOGITS
     coaction
    0.46
     endlich
    0.46
     менен
    0.46
     очередь
    0.46
    ্যেষ্ঠ
    0.42
    чні
    0.42
     naming
    0.42
    traded
    0.41
     grouping
    0.41
    isieren
    0.40
    Activations Density 0.000%

    No Known Activations