© 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. 212673
    Prev
    Next
    INDEX
    Explanations

    acknowledge and

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

    even with the disclaimer

    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
    ኛውም
    0.46
    ACON
    0.46
    юще
    0.45
    重量
    0.42
    ACLE
    0.42
    的三
    0.42
    纸
    0.41
    CCN
    0.41
    ComponentModel
    0.40
    JN
    0.40
    POSITIVE LOGITS
    ι
    0.66
     fizeram
    0.52
     পর্যাপ্ত
    0.50
     oznacza
    0.48
     persönlichen
    0.47
     trabal
    0.47
     americanos
    0.47
    lum
    0.46
     arter
    0.46
     enfl
    0.46
    Activations Density 0.001%

    No Known Activations