© 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. 81248
    Prev
    Next
    INDEX
    Explanations

    discussing specific entities or states

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

    self-reflection and assessment

    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
    囁
    0.56
    ナ
    0.55
    穏
    0.55
    一般的な
    0.54
    सेशन
    0.52
    言
    0.51
     Naomi
    0.50
    メイ
    0.50
    Ḍ
    0.50
    рів
    0.50
    POSITIVE LOGITS
    ee
    0.45
    కున్నారు
    0.44
    bow
    0.44
    ifiz
    0.42
    rao
    0.42
    bk
    0.40
     sele
    0.39
    ल्टा
    0.39
     shifted
    0.39
     lieber
    0.39
    Activations Density 0.000%

    No Known Activations