© 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. 14121
    Prev
    Next
    INDEX
    Explanations

    test scenario, script, storyline

    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
     ὑ
    0.90
     substandard
    0.85
    ocomplete
    0.83
     pouces
    0.83
    舢
    0.83
     deities
    0.78
     સર્
    0.78
     leggera
    0.77
    คองโก
    0.76
    𝔬
    0.75
    POSITIVE LOGITS
    al
    0.95
     رد
    0.79
     erst
    0.78
    ginas
    0.77
    trick
    0.77
    th
    0.74
    el
    0.73
    gens
    0.73
    er
    0.71
    edia
    0.70
    Activations Density 0.000%

    No Known Activations