© 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. 138579
    Prev
    Next
    INDEX
    Explanations

    approximately $0.04 billion

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

    qualified observations

    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
     знать
    0.52
     குறிப்பி
    0.51
     சுய
    0.49
     уйнарга
    0.47
    ⵕ
    0.47
     полити
    0.46
     कट्टर
    0.46
    キーワード
    0.46
     ურთიერთ
    0.45
     खासकर
    0.45
    POSITIVE LOGITS
     next
    0.48
    ৰ
    0.44
    шня
    0.43
     pancreatic
    0.43
     È
    0.42
     aliqu
    0.41
     east
    0.41
     obtainable
    0.41
     deficit
    0.41
     fhould
    0.41
    Activations Density 0.000%

    No Known Activations