© 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. 87365
    Prev
    Next
    INDEX
    Explanations

    roses, glory, and God

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

    monitoring and counting data

    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
    ня
    0.50
    ?\
    0.48
    is
    0.46
    urn
    0.45
     ста
    0.45
    हत
    0.44
    }$.
    0.44
    باشد
    0.44
    ция
    0.43
     ဂ
    0.43
    POSITIVE LOGITS
     Jeżeli
    0.52
    스가
    0.44
     topologically
    0.42
    যদি
    0.42
    工作人员
    0.42
     যদি
    0.41
     Phys
    0.41
     Dzięki
    0.41
     Jeden
    0.41
     বিচারপতি
    0.40
    Activations Density 0.000%

    No Known Activations