© 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. 138360
    Prev
    Next
    INDEX
    Explanations

    determined to go

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

    certain signal

    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
     milyon
    0.59
    綠
    0.55
    क्सी
    0.54
    म्भ
    0.54
    ىر
    0.53
     strumento
    0.53
    ᾳ
    0.52
     edilir
    0.52
     Kxb
    0.51
     değişik
    0.50
    POSITIVE LOGITS
    ≒
    0.64
    ――
    0.60
     거짓
    0.57
    ・・・
    0.56
     suppressing
    0.55
    〜
    0.54
     인간
    0.53
     확실
    0.53
     거기
    0.53
     굉장
    0.53
    Activations Density 0.051%

    No Known Activations