© 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. 85987
    Prev
    Next
    INDEX
    Explanations

    websites

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

    making decisions about adoption

    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
    必須
    0.43
     scoop
    0.43
     shavings
    0.43
    พาะ
    0.42
     超
    0.41
     ৪০
    0.41
     চল্লিশ
    0.41
     พา
    0.40
     માત્ર
    0.40
     সর্ব
    0.40
    POSITIVE LOGITS
     Goodreads
    0.46
     ardından
    0.45
     Australien
    0.45
     sowie
    0.44
     Arzneim
    0.44
     Aquino
    0.43
     Polyn
    0.43
    ildi
    0.43
    ”
    0.42
    টিয়ে
    0.42
    Activations Density 0.008%

    No Known Activations