© 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. 169372
    Prev
    Next
    INDEX
    Explanations

    making different

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

    safe to use commercially earned free public

    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
    0
    0.50
     transfection
    0.47
     deteriorating
    0.46
     riser
    0.46
     DAC
    0.46
     warming
    0.46
     upang
    0.46
     hepatic
    0.45
     rescheduling
    0.45
     APT
    0.45
    POSITIVE LOGITS
    <0x98>
    0.51
    <0x93>
    0.48
    ába
    0.45
    վել
    0.45
    дон
    0.45
    nikiem
    0.45
    ించింది
    0.44
    roč
    0.43
    <0x85>
    0.43
    <0xB5>
    0.43
    Activations Density 0.001%

    No Known Activations