© 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. 116061
    Prev
    Next
    INDEX
    Explanations

    announcement or dumpsters

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

    "new" is relative

    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
    onato
    0.46
    VII
    0.44
    cooling
    0.44
    ossing
    0.44
    not
    0.43
    ended
    0.43
    定律
    0.43
    t
    0.42
     못
    0.42
    酗
    0.41
    POSITIVE LOGITS
     abduction
    0.55
     announcement
    0.54
     nueva
    0.54
     mensaje
    0.53
     venerable
    0.53
     nouvelle
    0.51
     new
    0.50
     yeni
    0.50
     announcements
    0.50
     frisk
    0.50
    Activations Density 0.001%

    No Known Activations