© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 65528
    Prev
    Next
    INDEX
    Explanations

    contact and inquiries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     voti
    -1.07
     GRATU
    -1.05
    Pcs
    -0.96
     poliuret
    -0.95
     corda
    -0.95
     fraude
    -0.95
    ???:
    -0.94
     mobilen
    -0.93
     Internasional
    -0.93
    Ṭ
    -0.93
    POSITIVE LOGITS
     contact
    1.34
     nabíz
    1.30
    请联系
    1.24
     можем
    1.23
     prosím
    1.18
     enquiries
    1.13
     Contact
    1.11
    Contact
    1.08
     negotiation
    1.07
    contact
    1.06
    Activations Density 0.031%

    No Known Activations