© 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. 104901
    Prev
    Next
    INDEX
    Explanations

    sentence endings and specific markers

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

    final answer boxing

    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
     viu
    0.47
     culmin
    0.45
     élèves
    0.41
     پڑھ
    0.40
     Billy
    0.40
     cohes
    0.39
    ᇁ
    0.39
    گی
    0.38
    افه
    0.38
    ेलो
    0.38
    POSITIVE LOGITS
     traceback
    0.40
    6
    0.40
     MNRAS
    0.39
    †
    0.39
    डर
    0.39
    ?;
    0.39
    Gaussian
    0.38
    ensington
    0.37
     declared
    0.37
    </td>
    0.37
    Activations Density 0.000%

    No Known Activations