© 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. 237074
    Prev
    Next
    INDEX
    Explanations

    school of life

    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
    รียม
    0.50
     lactation
    0.50
    𝒞
    0.50
    쉘
    0.50
    פ
    0.48
    喬
    0.46
    ἂ
    0.46
     mengurangi
    0.46
    біць
    0.46
    SING
    0.46
    POSITIVE LOGITS
     متعدد
    0.46
    1
    0.45
    ists
    0.45
     იყ
    0.44
    irc
    0.41
    ield
    0.41
    omb
    0.41
    gard
    0.41
    amp
    0.41
    gie
    0.40
    Activations Density 0.001%

    No Known Activations