© 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. 145328
    Prev
    Next
    INDEX
    Explanations

    academic and financial contexts

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

    years had etched

    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
    roleum
    0.52
     রক্ত
    0.47
    Specs
    0.44
     অক্সিজেন
    0.44
     પાણી
    0.43
    榄
    0.42
    Dont
    0.42
    newName
    0.42
    朢
    0.42
     слишком
    0.41
    POSITIVE LOGITS
     epistemology
    0.52
     estaba
    0.50
     accommodate
    0.50
     byly
    0.49
     najwy
    0.48
     epistem
    0.47
     discursive
    0.47
    czych
    0.47
    ミュ
    0.46
     instituciones
    0.46
    Activations Density 0.000%

    No Known Activations