© 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. 117558
    Prev
    Next
    INDEX
    Explanations

    offers, fees, prices

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

    providing explanations and resources

    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
     ,
    0.48
    +}
    0.47
    =?
    0.46
    律
    0.45
     mulut
    0.44
    方面
    0.44
    +]
    0.44
    داً
    0.44
    รง
    0.44
    ·
    0.44
    POSITIVE LOGITS
    segaretro
    0.58
     twierd
    0.48
     جشنواره
    0.44
    UserProg
    0.44
     Oekra
    0.44
    storeItem
    0.43
     Catawiki
    0.43
     meetup
    0.43
     způ
    0.43
     चुनौतियों
    0.43
    Activations Density 0.001%

    No Known Activations