© 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. 107360
    Prev
    Next
    INDEX
    Explanations

    business roles and activities

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

    understanding and focus

    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
     иг
    0.45
     Fabric
    0.45
     أساس
    0.45
     hierv
    0.44
    :+
    0.43
     colon
    0.43
     ezzel
    0.42
    的表现
    0.41
    しい
    0.41
     ignor
    0.41
    POSITIVE LOGITS
     경영
    0.52
    擢
    0.48
    ка
    0.47
    mediated
    0.46
    shirts
    0.46
     क्रांतिकारी
    0.46
    ງານ
    0.46
    י
    0.46
     borrowers
    0.45
    promised
    0.45
    Activations Density 0.000%

    No Known Activations