© 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. 238205
    Prev
    Next
    INDEX
    Explanations

    UCL damagewant toappear asall new

    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
     וש
    0.48
     fabricación
    0.47
    يدية
    0.46
     봅시다
    0.46
    זור
    0.46
    ייתה
    0.46
    ➊
    0.45
    恝
    0.44
    조건
    0.44
    ல்ல
    0.43
    POSITIVE LOGITS
    ASM
    0.48
     ASM
    0.46
     queued
    0.43
     values
    0.43
     levels
    0.43
     moan
    0.42
     overhang
    0.42
     ensure
    0.41
    uspended
    0.41
    </code>
    0.40
    Activations Density 0.001%

    No Known Activations