© 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. 19773
    Prev
    Next
    INDEX
    Explanations

    older man younger man

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

    weather conditions

    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
     plot
    0.42
    ポリシー
    0.42
    トレ
    0.39
     ベース
    0.39
    思想
    0.39
    :*
    0.39
    セール
    0.38
     repeatable
    0.38
    **
    0.38
    Plot
    0.37
    POSITIVE LOGITS
     playfully
    0.48
    nament
    0.40
    </footer>
    0.39
    વતી
    0.39
     পাঠিয়ে
    0.39
     Mouth
    0.39
    াতাড়ি
    0.39
    ḩ
    0.39
     Gere
    0.38
     यश
    0.38
    Activations Density 0.043%

    No Known Activations