© 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. 66006
    Prev
    Next
    INDEX
    Explanations

    section headers or keywords likely following context

    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
     induk
    -1.48
     kosme
    -1.37
     apparaissent
    -1.32
     individuel
    -1.31
     solides
    -1.27
     robuste
    -1.27
     illustre
    -1.27
     pavillon
    -1.27
     essentielle
    -1.26
     passende
    -1.23
    POSITIVE LOGITS
     that
    1.68
     it
    1.65
     technology
    1.23
     deschis
    1.20
     meetings
    1.18
     location
    1.14
     painful
    1.13
     folosi
    1.11
     tools
    1.10
     îmb
    1.09
    Activations Density 0.040%

    No Known Activations