© 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. 4457
    Prev
    Next
    INDEX
    Explanations

    training models

    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
    4
    0.62
    5
    0.59
    3
    0.53
    6
    0.52
    7
    0.48
    -
    0.47
    8
    0.47
    1
    0.47
    2
    0.46
    i
    0.44
    POSITIVE LOGITS
     biomark
    0.37
     obliga
    0.36
     annih
    0.35
     wrongdoing
    0.34
     reformas
    0.34
    اعری
    0.33
     financiero
    0.32
     ennemis
    0.32
     infringer
    0.32
     marít
    0.32
    Activations Density 0.000%

    No Known Activations