© 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. 7859
    Prev
    Next
    INDEX
    Explanations

    utilizing an, lets get, and then

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

    "leads to", "neither too", "Moonlight Sonata"

    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
    1
    0.47
    లో
    0.44
    afft
    0.44
    7
    0.43
    మే
    0.43
    ังก
    0.42
     Salaries
    0.41
    రిగ
    0.41
    2
    0.41
    জন
    0.40
    POSITIVE LOGITS
     regolare
    0.48
     upas
    0.47
     sağlay
    0.46
     बटन
    0.45
     पिन
    0.44
     bắn
    0.43
     "("
    0.43
    워크
    0.43
     übrigens
    0.43
     உள்ளன
    0.42
    Activations Density 0.000%

    No Known Activations