© 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. 225579
    Prev
    Next
    INDEX
    Explanations

    end of phrase/statement

    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
     horse
    0.48
    筹
    0.43
     chapter
    0.43
     ME
    0.43
     essay
    0.41
     consulting
    0.41
     lạ
    0.41
     `=`
    0.41
     Interface
    0.40
     cunt
    0.40
    POSITIVE LOGITS
    íduos
    0.52
    rollen
    0.49
    HasStarred
    0.48
    河北
    0.46
    TBL
    0.46
     విషయంలో
    0.46
    注意力
    0.46
    ية
    0.45
    ਸੀਂ
    0.45
    يه
    0.44
    Activations Density 0.000%

    No Known Activations