© 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. 12-GEMMASCOPE-2-RES-16K
    7. 7
    Prev
    Next
    INDEX
    Explanations

    attributions

    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_12_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
    वता
    0.48
     pathogenicity
    0.48
    ти
    0.48
    tudo
    0.47
    )&=
    0.46
    श्यक
    0.45
    ᅨ
    0.45
    wegs
    0.44
    দিগের
    0.44
     kammam
    0.44
    POSITIVE LOGITS
     The
    0.63
    The
    0.59
    the
    0.55
    ll
    0.55
    ir
    0.54
    daki
    0.51
    IA
    0.50
    al
    0.50
    d
    0.50
    و
    0.50
    Activations Density 0.710%

    No Known Activations