© 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. 80168
    Prev
    Next
    INDEX
    Explanations

    quality, domain, pesticides, vehicle

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

    vacuum energy

    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
    س
    0.51
    भूति
    0.51
    ហ៊
    0.50
    र्या
    0.48
    ногие
    0.48
    ୋ
    0.46
    ಏ
    0.45
    रो
    0.44
    াউন
    0.44
    量は
    0.44
    POSITIVE LOGITS
    。
    0.47
    ohn
    0.46
    êtes
    0.46
    oc
    0.45
    ado
    0.45
    aden
    0.45
    宣
    0.44
    edly
    0.43
    摄
    0.43
     Aden
    0.43
    Activations Density 0.001%

    No Known Activations