© 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. 164376
    Prev
    Next
    INDEX
    Explanations

    searching for

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

    linkages, Nodes, Numerics, context

    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
    ام
    0.48
    marginY
    0.48
    আ
    0.46
    ಮ
    0.46
    ="..\
    0.46
    ي
    0.46
    Α
    0.46
    收到
    0.45
    ନ
    0.45
    さて
    0.44
    POSITIVE LOGITS
     linkages
    0.53
     attendant
    0.52
     Nodes
    0.52
     aerospace
    0.52
     synchron
    0.49
     '//
    0.47
     Node
    0.47
     eight
    0.47
     tunnel
    0.47
     Noeud
    0.47
    Activations Density 0.001%

    No Known Activations