© 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. 973
    Prev
    Next
    INDEX
    Explanations

    email address

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

    professions and roles

    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
     kadang
    0.32
    į
    0.32
    疖
    0.32
    havior
    0.32
    ム
    0.31
    Entonces
    0.31
     supposing
    0.30
    𝑝
    0.30
    chmal
    0.30
    வதில்லை
    0.30
    POSITIVE LOGITS
     Launched
    0.47
     millennials
    0.43
     Millennials
    0.43
     CNBC
    0.42
     Vodafone
    0.41
     Etihad
    0.40
     đã
    0.39
     CEO
    0.39
     Fintech
    0.39
     fintech
    0.37
    Activations Density 0.000%

    No Known Activations