© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 68999
    Prev
    Next
    INDEX
    Explanations

    Indian TV series titles

    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
     beteken
    -1.10
    setResizable
    -1.08
    tispiece
    -1.03
     ziren
    -1.02
     cucchiai
    -1.02
     commences
    -1.02
     multicolore
    -1.02
     préc
    -1.01
     també
    -1.01
    特に
    -1.00
    POSITIVE LOGITS
     buque
    1.19
    ateral
    1.18
    ]}{
    1.13
     enfermera
    1.12
     family
    1.09
     zmieni
    1.09
     hospital
    1.09
    strual
    1.06
    athons
    1.05
    醯
    1.05
    Activations Density 0.005%

    No Known Activations