© 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. 34-GEMMASCOPE-RES-131K
    7. 57214
    Prev
    Next
    INDEX
    Explanations

    senior executive

    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_34/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
    不但
    -1.34
    不僅
    -1.27
     Although
    -1.27
     While
    -1.25
    不仅
    -1.24
     disposiciones
    -1.20
     afirmó
    -1.20
     sostuvo
    -1.19
     Though
    -1.16
     declaró
    -1.16
    POSITIVE LOGITS
    ~)
    1.55
     zoude
    1.52
     apartament
    1.48
     laboratorium
    1.48
     cuch
    1.47
    ~:
    1.45
     otel
    1.34
     suche
    1.34
     adecu
    1.34
     negros
    1.34
    Activations Density 0.345%

    No Known Activations