© 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. 169409
    Prev
    Next
    INDEX
    Explanations

    contextualizing concepts

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

    learning and discovery

    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
    계를
    0.47
    :"+
    0.46
     oddly
    0.46
    čku
    0.45
    ）；
    0.45
     rec
    0.45
    kaw
    0.44
     Tanj
    0.44
     antagonistic
    0.43
    *'
    0.43
    POSITIVE LOGITS
    โท
    0.53
    人々
    0.49
    ەش
    0.49
    潸
    0.47
     ponieważ
    0.47
    یث
    0.46
     pointwise
    0.46
     tessuto
    0.46
    وث
    0.45
    ریٹر
    0.45
    Activations Density 0.002%

    No Known Activations