© 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. 33001
    Prev
    Next
    INDEX
    Explanations

    CO, asset, inspection, riots

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

    understanding those mistakes

    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
    enia
    0.52
     நட்சத்திர
    0.51
     Haft
    0.50
     विचारक
    0.49
    ἧ
    0.48
    он
    0.47
     Flore
    0.47
    τη
    0.47
    χν
    0.47
     нен
    0.46
    POSITIVE LOGITS
    i
    0.61
     expatri
    0.54
    is
    0.47
    o
    0.47
     apples
    0.47
     blends
    0.46
     expats
    0.45
     ex
    0.44
     quilts
    0.44
     originally
    0.44
    Activations Density 0.000%

    No Known Activations