© 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. 199691
    Prev
    Next
    INDEX
    Explanations

    payment, Advisors, India, law

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

    target parents

    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
     négl
    0.54
    㑔
    0.49
    ائلة
    0.47
     wichtig
    0.46
    水口
    0.46
     chín
    0.46
     nước
    0.45
     organizações
    0.45
    𝕟
    0.44
    পরে
    0.44
    POSITIVE LOGITS
    ened
    0.52
    ening
    0.50
    assis
    0.46
    al
    0.45
     Stripe
    0.44
    EE
    0.44
    Akt
    0.43
    epi
    0.43
     exceed
    0.43
    Crazy
    0.42
    Activations Density 0.000%

    No Known Activations