© 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. 208624
    Prev
    Next
    INDEX
    Explanations

    introduces defining phrases

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

    factoring, precipitate, Past, movies, news, frequency

    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
     চেষ্টা
    0.51
     કેટલાક
    0.48
     देवगन
    0.46
     让
    0.46
     জায়গা
    0.46
    之路
    0.46
    <unused2125>
    0.46
     меч
    0.45
     ন্যায
    0.45
     দেশকে
    0.45
    POSITIVE LOGITS
     metallic
    0.48
     affiliation
    0.46
     oph
    0.46
     prejud
    0.46
    +
    0.45
     ank
    0.44
     aank
    0.43
     azo
    0.43
     nitrite
    0.43
     unemployment
    0.43
    Activations Density 0.001%

    No Known Activations