© 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. 164499
    Prev
    Next
    INDEX
    Explanations

    PMC Bibcode Get critical

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

    lists with structure or bullet points

    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
     I
    0.49
     equator
    0.46
    数
    0.46
     e
    0.44
     slides
    0.43
     undulating
    0.43
     slid
    0.43
     f
    0.43
     almost
    0.43
     obedience
    0.42
    POSITIVE LOGITS
     гульнявыя
    0.54
     поба
    0.49
    businessman
    0.49
    жерела
    0.49
    гети
    0.48
    Businessman
    0.47
     तक्र
    0.46
    hiq
    0.46
    Reasoner
    0.46
    DeleteItem
    0.46
    Activations Density 0.000%

    No Known Activations