© 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. 79967
    Prev
    Next
    INDEX
    Explanations

    Erinnyis

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

    legal and formal document formats, particularly court cases and obituaries.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     Garantía
    -1.24
     Nedir
    -1.21
    
    -1.19
     Then
    -1.18
    :
    -1.14
    coleccion
    -1.06
    theres
    -1.06
     ...
    -1.06
    xii
    -1.05
     edifício
    -1.05
    POSITIVE LOGITS
     will
    1.69
    จะมี
    1.35
    Beskrivelse
    1.30
     будет
    1.26
    Indien
    1.22
     and
    1.21
    Ingredi
    1.19
     Erwä
    1.18
    躊
    1.17
     his
    1.16
    Activations Density 0.001%

    No Known Activations