© 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. 39885
    Prev
    Next
    INDEX
    Explanations

    Q: Image caption. Carbonates

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

    copyright and license statements in code files.

    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
     also
    -1.08
     Jeg
    -0.97
     Schilder
    -0.90
    claimer
    -0.89
    Submission
    -0.89
    Související
    -0.88
     nagu
    -0.88
     often
    -0.88
     Secure
    -0.87
    autés
    -0.87
    POSITIVE LOGITS
     portavoz
    0.92
    kleidung
    0.89
     日
    0.85
     durante
    0.85
     jamás
    0.83
    Referencer
    0.82
    क्षा
    0.81
     coordon
    0.80
     uniquement
    0.80
    post
    0.80
    Activations Density 0.000%

    No Known Activations