© 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. 125795
    Prev
    Next
    INDEX
    Explanations

    no longer listed

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

    applying semantic rules

    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
     ดาว
    0.54
    ن
    0.51
     คูณ
    0.50
     entró
    0.50
     واخ
    0.49
    pq
    0.49
     忄
    0.48
     کا
    0.47
    preuves
    0.46
     ถาม
    0.46
    POSITIVE LOGITS
     little
    0.49
     metastable
    0.49
     yet
    0.49
     hopefully
    0.46
     embarazo
    0.46
    )'
    0.46
     Third
    0.45
    х
    0.45
     gosh
    0.44
     example
    0.44
    Activations Density 0.001%

    No Known Activations