© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 107
    Prev
    Next
    INDEX
    Explanations

    bag or Epic context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_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
    modes
    0.40
    activating
    0.38
    ს
    0.38
    ли
    0.37
    ценка
    0.37
    ление
    0.37
    变化
    0.36
     Ferté
    0.36
    𝐨
    0.36
    𝚌
    0.36
    POSITIVE LOGITS
    )|
    0.52
    )
    0.50
    );
    0.45
     Tämä
    0.40
     Series
    0.38
     hadn
    0.37
    "
    0.37
    )"
    0.36
     pled
    0.36
     someone
    0.36
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.