© 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. 193376
    Prev
    Next
    INDEX
    Explanations

    sentence terminal punctuation

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

    definitions and rules

    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
    痕
    0.46
    agun
    0.45
     dön
    0.44
    ังหว
    0.43
     madres
    0.43
     tweede
    0.41
     silah
    0.41
     beweg
    0.41
    MainNav
    0.40
    ربعة
    0.40
    POSITIVE LOGITS
    }\
    0.53
     ஆரோக்கிய
    0.50
    }>
    0.49
    ה
    0.46
    }\\
    0.45
    กฏ
    0.45
    }\,
    0.44
    script
    0.44
    cells
    0.44
    ஸ
    0.43
    Activations Density 0.001%

    No Known Activations