© 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. 160993
    Prev
    Next
    INDEX
    Explanations

    contextual phrase connectors

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

    punctuation and sentence breaks

    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
     unfair
    0.53
     in
    0.48
     junho
    0.46
     any
    0.46
    )]
    0.46
     ‏
    0.44
     Stewart
    0.44
     only
    0.43
    e
    0.42
     each
    0.42
    POSITIVE LOGITS
     ትንሽ
    0.59
     carénés
    0.53
     తీవ్ర
    0.51
    📖
    0.49
     倍
    0.48
    >,
    0.48
     aigus
    0.48
    textColour
    0.48
     ತುಂಬಾ
    0.47
     పూర్తిగా
    0.45
    Activations Density 0.000%

    No Known Activations