© 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. 21624
    Prev
    Next
    INDEX
    Explanations

    what one should do

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

    understanding concepts and relationships

    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
    ловек
    0.42
     वे
    0.42
    ალ
    0.42
     그
    0.41
    וב
    0.41
     cylinders
    0.39
     λί
    0.39
    পেক্ষ
    0.38
    鲟
    0.38
    èr
    0.38
    POSITIVE LOGITS
    ಚ್
    0.53
     পিঁপড়া
    0.47
     Komple
    0.46
     Subcommittee
    0.45
     बीटल
    0.45
     Xing
    0.43
    nak
    0.42
     allowable
    0.42
     ідэ
    0.42
     فريبي
    0.41
    Activations Density 0.000%

    No Known Activations