© 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. 248717
    Prev
    Next
    INDEX
    Explanations

    end of sentence followed by specific words

    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
    け
    0.50
    صی
    0.49
    委員
    0.49
    会の
    0.47
    らの
    0.46
    ί
    0.45
    вра
    0.45
    فی
    0.44
     Networks
    0.43
    ραγ
    0.43
    POSITIVE LOGITS
     ```
    0.49
     ದ
    0.49
     anis
    0.48
     cuestión
    0.48
     notícias
    0.48
     amantes
    0.48
     DIEGO
    0.48
     wodurch
    0.48
     leaned
    0.47
     diem
    0.47
    Activations Density 0.000%

    No Known Activations