© 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. 220699
    Prev
    Next
    INDEX
    Explanations

    hot food or drink

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

    self-contained instructions or actions

    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
    𝙄
    0.53
     romanzo
    0.52
     deciso
    0.50
     Tạo
    0.50
     traslad
    0.48
    jero
    0.48
     multitudes
    0.47
     pertin
    0.46
     creato
    0.46
    擇
    0.46
    POSITIVE LOGITS
     inflation
    0.46
    inflation
    0.44
     incubator
    0.43
     पाएंगे
    0.42
    どり
    0.42
     civilization
    0.41
     بدون
    0.41
     একাডেমিক
    0.41
     학
    0.40
    玄関
    0.40
    Activations Density 0.000%

    No Known Activations