© 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. 60902
    Prev
    Next
    INDEX
    Explanations

    delivery plan, skill area, physical altercation

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

    auxiliary verbs and status

    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
    傭
    0.47
     or
    0.41
     nonprofits
    0.41
     and
    0.39
     in
    0.39
     বুঝি
    0.39
     industrialists
    0.38
     (.
    0.38
     σ
    0.38
     απ
    0.38
    POSITIVE LOGITS
    ુંદર
    0.48
    datei
    0.46
     collegamento
    0.44
    母亲
    0.44
    ään
    0.43
    குழந்த
    0.43
    专辑
    0.43
    nikiem
    0.43
    ೬
    0.43
    ächst
    0.42
    Activations Density 0.000%

    No Known Activations