© 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. 69041
    Prev
    Next
    INDEX
    Explanations

    but, and, or

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

    learn nuances

    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
    رود
    0.51
     用
    0.48
    唳
    0.46
     habil
    0.45
    ２
    0.45
     fauna
    0.44
    Liste
    0.44
    沦
    0.44
     végétation
    0.43
    を食べ
    0.43
    POSITIVE LOGITS
    np
    0.57
    :
    0.54
    ia
    0.52
    !)
    0.48
    ):
    0.47
    বিশিষ্ট
    0.47
    ate
    0.46
    ari
    0.46
     pressed
    0.43
    !),
    0.43
    Activations Density 0.000%

    No Known Activations