© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 93863
    Prev
    Next
    INDEX
    Explanations

    linked co-occurring superhero bird Lovecraftian

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ঝল
    0.41
    $',
    0.39
    q
    0.39
    ']]
    0.38
    (",")
    0.38
    asp
    0.38
    qttr
    0.37
    !`
    0.37
    arxiv
    0.37
    ഖ
    0.37
    POSITIVE LOGITS
     formul
    0.47
     paralysis
    0.46
     enzym
    0.46
    בו
    0.44
    brahim
    0.44
     explor
    0.44
     efficacious
    0.44
     letter
    0.43
     isopropyl
    0.43
     письма
    0.43
    Activations Density 0.005%

    No Known Activations