© 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. 61353
    Prev
    Next
    INDEX
    Explanations

    phrase completion

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

    state of calm

    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
    Powerful
    0.47
    powerful
    0.47
    arse
    0.46
     सर्विस
    0.46
     バス
    0.46
    મ
    0.45
    豔
    0.45
     ベ
    0.45
     ਬ
    0.45
     cristall
    0.44
    POSITIVE LOGITS
     mornings
    0.46
     pursuant
    0.43
     retroactive
    0.42
    рное
    0.42
     evenings
    0.41
     separatist
    0.41
    ิน
    0.41
     hearings
    0.40
     cooperation
    0.40
    vline
    0.39
    Activations Density 0.000%

    No Known Activations