© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86247
    Prev
    Next
    INDEX
    Explanations

    organization member invites

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

    This neuron detects terms relating to permissions and access control—words about private/repos, grants, organization or team membership and related policy.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    刺激
    -1.29
     we
    -1.26
    男
    -1.25
    WARNINGS
    -1.24
    를
    -1.20
    Недостатки
    -1.20
    gemeester
    -1.18
     Of
    -1.14
    stdc
    -1.13
     PUSTAKA
    -1.13
    POSITIVE LOGITS
     who
    1.61
     slechts
    1.38
    only
    1.38
    érêt
    1.38
    どうやって
    1.33
    當時
    1.32
     când
    1.30
    却被
    1.30
    ໂ
    1.23
     dacă
    1.23
    Activations Density 0.078%

    No Known Activations