© 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. 75211
    Prev
    Next
    INDEX
    Explanations

    owned island

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

    parentheticals and stage directions

    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
    рна
    0.41
    &#
    0.40
    ignes
    0.40
    ersiz
    0.39
    Meu
    0.39
     délai
    0.39
     headwinds
    0.39
     මත
    0.38
     thawed
    0.38
    ह्
    0.38
    POSITIVE LOGITS
    剡
    0.52
     Career
    0.51
     getNode
    0.47
     proyecto
    0.46
     Notebook
    0.46
     Michaelmas
    0.46
     ashamed
    0.45
     Creative
    0.45
     Doctorate
    0.45
    CLUDING
    0.45
    Activations Density 0.001%

    No Known Activations