© 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. 5973
    Prev
    Next
    INDEX
    Explanations

    services following housing or president

    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
    顺
    0.40
    ферен
    0.36
    躏
    0.36
    ёз
    0.35
    赧
    0.35
    తిక
    0.34
    圄
    0.34
    សុ
    0.34
     தலைநக
    0.33
    MaxLength
    0.33
    POSITIVE LOGITS
     Sty
    0.37
     alé
    0.34
     Eric
    0.33
     adhere
    0.33
     pour
    0.33
     mentally
    0.33
     マット
    0.33
     instill
    0.32
     Matt
    0.32
    eri
    0.32
    Activations Density 0.000%

    No Known Activations