© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 119917
    Prev
    Next
    INDEX
    Explanations

    protected email addresses

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

    text indicating removed, hidden, or redacted content such as links, email addresses, or other information that has been censored or protected.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    おわりに
    -1.34
    你和
    -1.33
     to
    -1.31
    ヨーロ
    -1.30
    狐狸
    -1.23
    スイーツ
    -1.18
     duyg
    -1.16
     integrates
    -1.16
     Welche
    -1.15
    itespace
    -1.14
    POSITIVE LOGITS
    owego
    1.49
     previous
    1.41
    nesses
    1.35
    foundland
    1.30
     proximité
    1.24
    phobia
    1.24
    haped
    1.23
    сько
    1.23
    گیری
    1.23
    dited
    1.21
    Activations Density 0.071%

    No Known Activations