© 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. 197710
    Prev
    Next
    INDEX
    Explanations

    Alcoholic Beverage, malware, books, Office

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

    flat earthers or terraplanismo

    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
     casings
    0.47
     homomorphisms
    0.46
    찡
    0.45
     francs
    0.44
     மஹ
    0.43
    hashtag
    0.42
     writs
    0.42
    حضرت
    0.42
     savages
    0.42
    microseconds
    0.41
    POSITIVE LOGITS
     Alcoholic
    0.47
     ஒன்ற
    0.46
     Beverage
    0.46
    ˑ
    0.45
     விழு
    0.45
     ecmaVersion
    0.45
     প্রভৃতির
    0.44
    ൂ
    0.44
     Vicar
    0.44
    ępu
    0.43
    Activations Density 0.002%

    No Known Activations