© 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. 252066
    Prev
    Next
    INDEX
    Explanations

    technical concepts

    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
    𝐰
    0.52
    ur
    0.51
     ಬಹಳ
    0.51
    esterly
    0.48
    arr
    0.46
     ভেঙ্গে
    0.45
     இரத்த
    0.45
    kick
    0.45
     Биз
    0.45
    ា
    0.44
    POSITIVE LOGITS
     node
    1.31
     Node
    1.20
    node
    1.13
     nodes
    1.08
     getNode
    1.07
    节点
    1.04
     Nodes
    1.02
     nodo
    1.02
     Knoten
    1.00
     nod
    1.00
    Activations Density 0.010%

    No Known Activations