© 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. 88120
    Prev
    Next
    INDEX
    Explanations

    positive states and conditions

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

    winning or training probabilities

    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
     наличие
    0.56
     자세
    0.47
    iende
    0.46
     ditambah
    0.45
    حم
    0.44
    이면
    0.44
     dengan
    0.44
    奭
    0.43
    崗
    0.43
    щения
    0.42
    POSITIVE LOGITS
     nombr
    0.49
    〆
    0.48
    NVIC
    0.47
     Lester
    0.47
     guia
    0.46
    AIR
    0.46
     fortunately
    0.46
     spinor
    0.46
    ItemsSource
    0.45
     austri
    0.45
    Activations Density 0.001%

    No Known Activations