© 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. 60683
    Prev
    Next
    INDEX
    Explanations

    Qualifying Examination

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

    sequences describing LLM comparisons

    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
    AR
    0.50
    B
    0.50
     اخذت
    0.46
    AT
    0.46
    cut
    0.45
    pulse
    0.45
    Rp
    0.44
    Bk
    0.44
    OT
    0.44
     tiveram
    0.44
    POSITIVE LOGITS
     ensu
    0.46
    鍝
    0.45
     conceptions
    0.43
     visions
    0.43
     notions
    0.42
     mansions
    0.42
     convexe
    0.42
     Exceptional
    0.42
    毘
    0.42
     excepcional
    0.41
    Activations Density 0.000%

    No Known Activations