© 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. 73137
    Prev
    Next
    INDEX
    Explanations

    river and home again

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

    philosophical paradoxes and concepts

    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
    bytecode
    0.43
     بای
    0.42
     хозяй
    0.40
     바이
    0.40
     plague
    0.39
     रखता
    0.39
    obr
    0.38
    >",
    0.38
    KeyPair
    0.38
    Pharmac
    0.38
    POSITIVE LOGITS
     Greek
    0.44
     Greeks
    0.42
     Mater
    0.41
    인더
    0.41
     mater
    0.40
     Giants
    0.40
    cliff
    0.40
     river
    0.40
     brook
    0.39
     California
    0.39
    Activations Density 0.007%

    No Known Activations