© 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. 9210
    Prev
    Next
    INDEX
    Explanations

    number followed by +

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

    linear relationship, action verbs, equations

    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
     matur
    0.48
     Eaton
    0.47
     matures
    0.46
    cx
    0.45
    .*
    0.45
     matéri
    0.45
     चिह्नित
    0.45
     I
    0.45
     matured
    0.45
     erw
    0.44
    POSITIVE LOGITS
    ewnętr
    0.53
    ოველ
    0.47
    订阅
    0.45
     повлия
    0.45
    JsonResponse
    0.42
     வெளி
    0.42
    वण्यात
    0.41
     ইন্দু
    0.40
     తీవ్ర
    0.40
    ლე
    0.40
    Activations Density 0.000%

    No Known Activations