© 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-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 13413
    Prev
    Next
    INDEX
    Explanations

    counter narrative or argument

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hedge
    2.66
    ्टी
    2.65
    ณิต
    2.56
    啉
    2.50
     HttpException
    2.49
    ся
    2.47
    லாத
    2.41
    釋
    2.36
    ㄒ
    2.36
    ょ
    2.35
    POSITIVE LOGITS
    म
    3.34
    ع
    3.10
    an
    3.08
    м
    3.07
    SourceObject
    3.00
    र
    2.82
    间的
    2.61
    asas
    2.59
    isasi
    2.48
    ۰
    2.47
    Activations Density 0.007%

    No Known Activations