© 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. 86053
    Prev
    Next
    INDEX
    Explanations

    images and videos

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

    common stereotype

    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
    ală
    0.48
     प्रूफ
    0.48
    킁
    0.46
    ILS
    0.45
    лна
    0.44
    Ils
    0.43
    Chin
    0.43
    嘤
    0.43
    Ņ
    0.42
    Hex
    0.42
    POSITIVE LOGITS
     considère
    0.59
     texte
    0.53
     рассматри
    0.51
     imagenes
    0.49
    colours
    0.49
    صور
    0.48
     vídeos
    0.47
    '/>
    0.47
    考慮
    0.47
     consider
    0.47
    Activations Density 0.000%

    No Known Activations