© 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. 203700
    Prev
    Next
    INDEX
    Explanations

    specific conditions and terms

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

    created by or from

    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
     quantitatively
    0.47
     dusty
    0.46
     waxes
    0.45
    alassem
    0.45
     quantifiable
    0.45
     quantized
    0.45
     woven
    0.44
    ட
    0.44
     irritating
    0.44
     pleasantly
    0.43
    POSITIVE LOGITS
    dere
    0.46
    剩
    0.45
    开头
    0.44
     चैंपियनशिप
    0.43
    nament
    0.43
     usia
    0.43
    ভাস
    0.41
     adına
    0.41
     বুঝ
    0.40
    jä
    0.40
    Activations Density 0.001%

    No Known Activations