© 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. 104791
    Prev
    Next
    INDEX
    Explanations

    liability whatsoever, aware of, allows you to

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

    duplicate items, solutions, harbors, revelations

    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
     соеди
    0.55
     зберіга
    0.52
    聳
    0.51
    hipping
    0.50
     ponú
    0.50
    🅴
    0.50
    odigd
    0.49
     思っ
    0.48
     使っ
    0.48
    𝗛
    0.48
    POSITIVE LOGITS
    /////////////
    0.47
     Defines
    0.44
     ordination
    0.43
     holen
    0.43
     eventdata
    0.41
    හෝ
    0.40
     divergences
    0.40
     notebooks
    0.40
    론
    0.39
    フラン
    0.39
    Activations Density 0.001%

    No Known Activations