© 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. 20612
    Prev
    Next
    INDEX
    Explanations

    the oven or set

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

    specialization creates blind spots

    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
     各
    0.50
     Bull
    0.49
     School
    0.48
     Working
    0.47
     Use
    0.47
    wissenschaft
    0.46
     Success
    0.46
     Mom
    0.46
     Open
    0.45
     Significant
    0.45
    POSITIVE LOGITS
    也許
    0.47
     অবশেষে
    0.44
     পারে
    0.43
    слен
    0.43
    આ
    0.43
    RawContext
    0.42
     advertised
    0.42
    ştir
    0.41
    ại
    0.41
     apologised
    0.41
    Activations Density 0.000%

    No Known Activations