© 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. 208236
    Prev
    Next
    INDEX
    Explanations

    written expression, based on, thought, enzymes

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

    "She Found", "She Opened"

    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
    어
    0.51
    시
    0.49
    가
    0.49
    酒
    0.47
    alcohol
    0.46
    警告
    0.46
    実
    0.46
    лакти
    0.45
    야
    0.45
    split
    0.45
    POSITIVE LOGITS
     নিঃস
    0.47
     innovate
    0.45
     initiate
    0.45
    чением
    0.44
     নির্ভ
    0.43
     end
    0.43
     bring
    0.43
     couple
    0.42
     निर्
    0.41
     enga
    0.41
    Activations Density 0.002%

    No Known Activations