© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48887
    Prev
    Next
    INDEX
    Explanations

    halogens and chlorides

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

    chemical formulas and compounds, particularly those containing chloride (Cl) and other inorganic salts.

    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_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
     Ön
    -0.89
     Benedikt
    -0.85
    Lee
    -0.85
     ricordo
    -0.82
    ParallelGroup
    -0.79
     your
    -0.79
    にん
    -0.78
    azah
    -0.77
    ५
    -0.76
    Ƅ
    -0.74
    POSITIVE LOGITS
     solution
    0.96
    omyelitis
    0.80
    țională
    0.77
    Adress
    0.77
    )]$
    0.75
    Groovy
    0.75
    引起了
    0.74
    Vehicles
    0.73
    Useless
    0.73
    diep
    0.73
    Activations Density 0.041%

    No Known Activations