© 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. 155003
    Prev
    Next
    INDEX
    Explanations

    library, players, control, bills

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

    women doing

    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
    ｺ
    0.49
    க்கூ
    0.46
     мол
    0.46
     plasticity
    0.45
     সমাজের
    0.44
     vectorial
    0.44
     არ
    0.44
    uità
    0.43
    弁
    0.43
    gebnis
    0.43
    POSITIVE LOGITS
     Kamala
    0.49
     Kayla
    0.45
     Secured
    0.45
     Vendor
    0.45
     Vendors
    0.45
     Comptroller
    0.44
     Fayetteville
    0.44
     Jennifer
    0.44
    Washington
    0.43
    George
    0.43
    Activations Density 0.001%

    No Known Activations