© 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. 13623
    Prev
    Next
    INDEX
    Explanations

    affiliation and candidacy

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

    traditional details

    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
     दर्जन
    0.41
     வேகமாக
    0.41
     тяже
    0.40
     последний
    0.40
    豪华
    0.39
    苋
    0.39
     кілька
    0.38
     سریع
    0.38
    itian
    0.38
     большей
    0.38
    POSITIVE LOGITS
    不存在
    0.43
     deference
    0.42
     affiliation
    0.41
     candidacy
    0.40
     postulate
    0.40
     ({\
    0.40
    ・
    0.39
     contribution
    0.38
     والت
    0.38
    affiliation
    0.38
    Activations Density 0.000%

    No Known Activations