© 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. 222367
    Prev
    Next
    INDEX
    Explanations

    after than from

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

    code and text formatting

    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
    ዘጋ
    0.49
     mediocre
    0.48
     getN
    0.48
     đa
    0.47
     더
    0.46
    aný
    0.45
     너
    0.45
     foreseeable
    0.44
     tópico
    0.44
    ಗ್ಗ
    0.44
    POSITIVE LOGITS
    Assets
    0.47
    olics
    0.46
    Markets
    0.45
    Bundes
    0.44
    <div>
    0.43
    कों
    0.43
    0
    0.43
     Assets
    0.42
     wird
    0.42
    :
    0.42
    Activations Density 0.001%

    No Known Activations