© 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. 201574
    Prev
    Next
    INDEX
    Explanations

    it can

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

    detailed spectroscopic analysis

    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
     Minus
    0.43
     Putting
    0.42
     Por
    0.41
     minus
    0.41
     por
    0.40
     porcelain
    0.40
    慈善
    0.39
    涧
    0.39
     porch
    0.38
     house
    0.38
    POSITIVE LOGITS
    dense
    0.48
    heavy
    0.46
    gathered
    0.46
     ભારે
    0.45
     істори
    0.45
    color
    0.44
    সজ্জিত
    0.44
    ወሰ
    0.43
    ದೇ
    0.43
    ದೆ
    0.43
    Activations Density 0.001%

    No Known Activations