© 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. 218486
    Prev
    Next
    INDEX
    Explanations

    free copy available on website

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

    list descriptions and categories

    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
     wavelet
    0.48
     severe
    0.47
     nematode
    0.46
     typewriter
    0.44
     μ
    0.43
     two
    0.43
     realistic
    0.43
     trophy
    0.42
     muon
    0.42
     ritual
    0.42
    POSITIVE LOGITS
    的文章
    0.50
     artik
    0.46
    ាំង
    0.46
     الدين
    0.46
     Nachrichten
    0.45
    }$).
    0.44
    ٩
    0.44
     தொடர்ப
    0.43
    倰
    0.43
    ビネット
    0.43
    Activations Density 0.001%

    No Known Activations