© 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. 231840
    Prev
    Next
    INDEX
    Explanations

    gold zipper

    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
     comfortable
    0.51
    v
    0.51
    aj
    0.47
    h
    0.46
    и
    0.46
    nt
    0.45
     o
    0.44
    comfortable
    0.44
    в
    0.44
     playback
    0.43
    POSITIVE LOGITS
    য়াছে
    0.52
     ধ্বংস
    0.52
    Chunk
    0.52
     সহিংসতার
    0.51
     আলু
    0.50
    deployRoot
    0.50
    ński
    0.49
     হামলার
    0.49
     تباہ
    0.49
     denaro
    0.48
    Activations Density 0.001%

    No Known Activations