© 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. 172431
    Prev
    Next
    INDEX
    Explanations

    cause or outcome

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

    likely be reported

    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
     metodología
    0.50
     hybr
    0.48
    ეს
    0.46
    髂
    0.45
     customPlot
    0.44
     metodologia
    0.44
    ერ
    0.44
     vidéos
    0.44
    ⵅ
    0.43
    耖
    0.43
    POSITIVE LOGITS
     worsened
    0.50
     scrapped
    0.47
     dishon
    0.45
     impairs
    0.44
     detriment
    0.43
     impeded
    0.43
     disliked
    0.42
     Canada
    0.42
    の原因
    0.42
     причиной
    0.41
    Activations Density 0.001%

    No Known Activations