© 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. 231372
    Prev
    Next
    INDEX
    Explanations

    aggregate quantity and link

    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
     Rear
    0.53
    も見
    0.51
    箖
    0.48
    殄
    0.48
    表面
    0.46
     Phylogenetic
    0.46
     Surface
    0.46
    曾在
    0.46
    呂
    0.45
     Things
    0.45
    POSITIVE LOGITS
    tors
    0.54
    nj
    0.53
    rangle
    0.48
    tor
    0.48
    ING
    0.48
    atr
    0.48
     да
    0.47
    da
    0.47
    ci
    0.47
    matrix
    0.47
    Activations Density 0.001%

    No Known Activations