© 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. 194567
    Prev
    Next
    INDEX
    Explanations

    interact with, per turn, ANVISA audits, Indesit

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

    PHP web development

    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
    ø
    0.52
     climbs
    0.51
    ht
    0.49
     that
    0.49
    java
    0.49
    als
    0.47
    jø
    0.47
    ſ
    0.47
    üdis
    0.46
    jt
    0.46
    POSITIVE LOGITS
    اهای
    0.47
    态度
    0.47
    िले
    0.46
     நாட்க
    0.44
    领域的
    0.42
     தயாரி
    0.42
    哲学
    0.42
     සම
    0.41
    ULTURAL
    0.41
    ंटर
    0.41
    Activations Density 0.000%

    No Known Activations