© 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. 95663
    Prev
    Next
    INDEX
    Explanations

    aspect, experience, adding, names, page, review

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

    provisioning, cost, scale, PON, Millis

    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
    newValue
    0.55
    ampshire
    0.53
     جھنڈ
    0.52
     ஆரம்ப
    0.49
     وهنا
    0.49
     اسرائیل
    0.49
     kwamba
    0.48
     એ
    0.48
    fieldContext
    0.47
    hamcrest
    0.46
    POSITIVE LOGITS
     provisioning
    0.50
     pollutant
    0.46
     marginal
    0.44
     regeneration
    0.43
    脫
    0.43
    屠
    0.43
     prognosis
    0.42
     উৎপ
    0.42
     subscribing
    0.42
     menu
    0.41
    Activations Density 0.000%

    No Known Activations