© 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. 21497
    Prev
    Next
    INDEX
    Explanations

    dumpster, identifiable, hosting, infinity, proceeding

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

    identity and exposure

    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
     …
    0.44
    ˂
    0.42
     tremble
    0.40
    trem
    0.40
     ..
    0.39
    ynch
    0.38
     ….
    0.38
     avert
    0.38
     لهذه
    0.37
    ."
    0.37
    POSITIVE LOGITS
     yazı
    0.42
     artisan
    0.42
    燔
    0.41
     étroit
    0.40
     কম্পিউ
    0.39
     tedesco
    0.39
     tedes
    0.39
     Schlaf
    0.39
     negozi
    0.39
     descub
    0.38
    Activations Density 0.000%

    No Known Activations