© 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. 172455
    Prev
    Next
    INDEX
    Explanations

    event outcomes

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

    explanations for calculation, cause, revenue, winning, related, backup, plans

    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
     SDR
    0.54
     FT
    0.53
     marít
    0.50
     NDR
    0.49
    𝗢
    0.48
    倸
    0.48
     BELL
    0.47
     embryonic
    0.47
    À
    0.47
     Theoretically
    0.47
    POSITIVE LOGITS
    les
    0.44
    ئة
    0.44
    cz
    0.43
    cs
    0.42
     vodi
    0.42
    0.42
    enos
    0.42
     routines
    0.42
    eful
    0.42
    attoos
    0.42
    Activations Density 0.001%

    No Known Activations