© 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. 122077
    Prev
    Next
    INDEX
    Explanations

    want to

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

    want to

    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
    wxr
    0.46
    preset
    0.46
    terminology
    0.44
    taxonomy
    0.44
     poorest
    0.43
    placeholder
    0.42
    persky
    0.42
    5
    0.42
    ală
    0.41
    rss
    0.41
    POSITIVE LOGITS
     Multicolor
    0.51
    λέ
    0.44
     finne
    0.44
     GIVE
    0.44
    holung
    0.43
    講
    0.42
     Suu
    0.41
    লীর
    0.41
     give
    0.41
     Rural
    0.40
    Activations Density 0.001%

    No Known Activations