© 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. 10714
    Prev
    Next
    INDEX
    Explanations

    codes followed by punctuation

    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
     Alors
    0.40
     undertaken
    0.39
    *-
    0.39
     strike
    0.37
    शिवाय
    0.36
     scaffold
    0.36
     cotid
    0.36
     pre
    0.35
     Pren
    0.35
     الأز
    0.35
    POSITIVE LOGITS
    જુ
    0.42
    ದ್ದರಿಂದ
    0.41
    noof
    0.41
    úst
    0.40
    廻
    0.40
    줍
    0.40
    埓
    0.39
    সো
    0.39
     adhé
    0.39
    Всем
    0.39
    Activations Density 0.000%

    No Known Activations