© 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. 187907
    Prev
    Next
    INDEX
    Explanations

    family, prevention, partners, facilities

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

    financial and business contexts

    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
     unpopular
    0.52
     islas
    0.51
    自治
    0.49
     Dadurch
    0.48
    邑
    0.48
     馬
    0.48
    一次
    0.47
     frecuente
    0.47
     unsound
    0.47
    揍
    0.47
    POSITIVE LOGITS
    financial
    0.52
    hat
    0.51
     मिळत
    0.50
    mountain
    0.50
    infinity
    0.49
    thon
    0.49
    mary
    0.48
    hotel
    0.47
    Mountain
    0.46
    tery
    0.46
    Activations Density 0.001%

    No Known Activations