© 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. 7414
    Prev
    Next
    INDEX
    Explanations

    segment tree

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

    partition by algorithm

    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
    嬅
    0.61
    🏤
    0.61
    ädchen
    0.60
    nashville
    0.59
    🏦
    0.59
    Allister
    0.59
    釀
    0.59
    ernacle
    0.57
    🏽
    0.57
    เชสเตอร์
    0.57
    POSITIVE LOGITS
     maxn
    0.80
     XOR
    0.65
     memset
    0.64
     modulo
    0.63
    ;++
    0.63
     [&](
    0.63
     compute
    0.61
     Gauss
    0.61
    ++
    0.59
    xor
    0.59
    Activations Density 0.001%

    No Known Activations