© 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. 11867
    Prev
    Next
    INDEX
    Explanations

    tree structure and code snippets

    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
     declarative
    0.86
     NSC
    0.82
     tangential
    0.80
     PSO
    0.80
     NTFS
    0.79
    apixel
    0.79
     communal
    0.79
     À
    0.78
     scalable
    0.78
     CX
    0.76
    POSITIVE LOGITS
    ب
    0.82
    ▓
    0.81
    OCKET
    0.79
    یا
    0.78
    Dimethyl
    0.77
    크
    0.75
    BLY
    0.75
    LEV
    0.74
    ميل
    0.74
    URED
    0.74
    Activations Density 0.001%

    No Known Activations