© 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. 116921
    Prev
    Next
    INDEX
    Explanations

    offset steep cuts

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

    sports or objects

    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
     GÉN
    0.60
     ಇರುವ
    0.55
     তড়
    0.50
     பின்ப
    0.48
     observación
    0.47
     MARRI
    0.47
     だけ
    0.46
    覬
    0.46
     exfoli
    0.46
     circulación
    0.46
    POSITIVE LOGITS
    Cabinet
    0.49
    Regional
    0.49
    чен
    0.48
     Red
    0.46
    Due
    0.46
    Stock
    0.46
    \
    0.46
    Cities
    0.46
    Red
    0.45
    Opening
    0.45
    Activations Density 0.002%

    No Known Activations