© 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. 104792
    Prev
    Next
    INDEX
    Explanations

    zip fly

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

    odd number

    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
    ettek
    0.49
    ()->
    0.48
    Customers
    0.48
     సంబంధించిన
    0.47
     بسبب
    0.47
    Dispatch
    0.46
    dim
    0.46
    ങ്കിലും
    0.46
    ْر
    0.46
    Removed
    0.46
    POSITIVE LOGITS
     persuas
    0.49
     estimates
    0.49
     humans
    0.48
     tingkat
    0.48
     forensics
    0.47
     penit
    0.46
     genomics
    0.45
     relays
    0.45
     roads
    0.44
     permutations
    0.44
    Activations Density 0.001%

    No Known Activations