© 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. 110762
    Prev
    Next
    INDEX
    Explanations

    sheep , breakfast , saw , chips

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

    what you trying to do

    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
    *;
    0.49
     kuvvet
    0.46
     многое
    0.44
    ściej
    0.43
     maw
    0.43
    j
    0.42
     parties
    0.42
    praw
    0.42
     Upt
    0.42
     kaw
    0.41
    POSITIVE LOGITS
    前的
    0.48
     ऑक्साइड
    0.47
    锕
    0.46
    表示
    0.46
     ভারতীয়
    0.46
    居
    0.46
    મ
    0.45
    スーパー
    0.45
     অ্যালবাম
    0.45
    錒
    0.44
    Activations Density 0.000%

    No Known Activations