© 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. 75006
    Prev
    Next
    INDEX
    Explanations

    change and diagnosis

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

    Coastal Scenery or impact of

    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
     Per
    0.52
     Z
    0.50
     F
    0.44
    Iw
    0.44
      
    0.42
     Morris
    0.42
    feri
    0.42
     is
    0.42
     L
    0.42
     C
    0.41
    POSITIVE LOGITS
    ंसर
    0.53
     катастро
    0.48
     cambiamento
    0.46
     변화
    0.46
    竞争力
    0.46
     পরিবর্তন
    0.45
    ેચ્છ
    0.45
    ূর্তি
    0.44
    锲
    0.44
    幼儿
    0.44
    Activations Density 0.000%

    No Known Activations