© 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. 141588
    Prev
    Next
    INDEX
    Explanations

    helicopter ride

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

    questions followed by "Seriously?" or exclamations

    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
     Inge
    0.55
     dispel
    0.54
     relocate
    0.54
     つ
    0.54
     liquidate
    0.52
     idempot
    0.52
     Heron
    0.50
     Vec
    0.49
     Subtle
    0.49
     attuale
    0.49
    POSITIVE LOGITS
    foundation
    0.48
    css
    0.44
    пу
    0.43
    ἆ
    0.42
    level
    0.41
    four
    0.41
    ర్‌
    0.41
    fourth
    0.41
    iii
    0.40
    six
    0.40
    Activations Density 0.000%

    No Known Activations