© 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. 8205
    Prev
    Next
    INDEX
    Explanations

    various descriptions that follow specific words

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

    chapters and bad anatomy

    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
    ﻟ
    0.56
    он
    0.51
    АР
    0.49
     его
    0.45
    ೋಟ
    0.45
    Minneapolis
    0.45
    彼の
    0.44
    originally
    0.44
    াব্য
    0.44
    颯
    0.44
    POSITIVE LOGITS
     Schr
    0.57
     acudir
    0.50
     đỡ
    0.50
     Matthe
    0.49
     actively
    0.47
     Schreiber
    0.47
     Kakkar
    0.47
     comando
    0.46
     Matth
    0.46
     ẩm
    0.46
    Activations Density 0.000%

    No Known Activations