© 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. 154670
    Prev
    Next
    INDEX
    Explanations

    best interests

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

    behavioral or fortunes

    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
    ેલી
    0.56
    |.|.|
    0.54
    ос
    0.50
    兗
    0.49
     كرة
    0.48
    уд
    0.47
     üzeri
    0.47
    errno
    0.47
    价值
    0.47
    ())));
    0.46
    POSITIVE LOGITS
     gua
    0.44
     द्वितीय
    0.43
     Guillermo
    0.41
    rophages
    0.40
     Zal
    0.40
     ary
    0.39
     peptides
    0.39
    brains
    0.39
     MainForm
    0.39
     tribunals
    0.38
    Activations Density 0.001%

    No Known Activations