© 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. 248784
    Prev
    Next
    INDEX
    Explanations

    price and size

    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
    सर्गिक
    0.44
    racing
    0.43
     expressway
    0.43
     Nicaragua
    0.42
     foodie
    0.42
    v
    0.42
    retail
    0.42
     Vegas
    0.41
    दम
    0.41
    y
    0.41
    POSITIVE LOGITS
    ezers
    0.52
     മുൻ
    0.50
    春节
    0.49
    *)
    0.48
     বইটি
    0.48
    ە
    0.48
    的這個
    0.48
    زي
    0.47
     خش
    0.46
    샀
    0.46
    Activations Density 0.000%

    No Known Activations