© 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. 49085
    Prev
    Next
    INDEX
    Explanations

    punctuation and conjunctions

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

    connecting lists or clauses

    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
    ને
    0.50
    restrial
    0.46
    .[/
    0.46
    ujacy
    0.44
    对象的
    0.43
     permettant
    0.42
     فى
    0.42
    ۇر
    0.40
     blevet
    0.40
     ==============
    0.39
    POSITIVE LOGITS
     會
    0.48
     אחד
    0.44
    ᅮ
    0.44
     אחת
    0.43
    ಇ
    0.43
     दस्ता
    0.43
     cena
    0.41
     inquis
    0.41
    名稱
    0.41
     batter
    0.40
    Activations Density 0.048%

    No Known Activations