© 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. 19415
    Prev
    Next
    INDEX
    Explanations

    charity, library, and product related questions

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

    company reports, business, technical components

    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
    @
    0.41
     significantly
    0.40
     facilita
    0.40
    0.39
     basada
    0.39
     multifunctional
    0.37
    flex
    0.36
    vertical
    0.36
     permite
    0.36
    assurance
    0.36
    POSITIVE LOGITS
    MaxScaler
    0.47
    旄
    0.43
    响
    0.42
    的时间
    0.42
    抔
    0.42
     ను
    0.41
    烝
    0.41
    狲
    0.41
    UnderTest
    0.40
    垕
    0.40
    Activations Density 0.002%

    No Known Activations