© 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. 16039
    Prev
    Next
    INDEX
    Explanations

    correct or incorrect

    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
    ло
    0.76
     замени
    0.73
    ne
    0.72
    bill
    0.70
    lesh
    0.69
     fears
    0.69
    мана
    0.69
    ل
    0.69
     threatens
    0.67
     може
    0.66
    POSITIVE LOGITS
    掫
    0.89
    \}=\
    0.85
     setembro
    0.85
    }}[
    0.85
     corretamente
    0.84
    acidade
    0.82
    }}=
    0.82
     novembro
    0.81
    úč
    0.80
    }}^{(
    0.79
    Activations Density 0.000%

    No Known Activations