© 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-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 1120
    Prev
    Next
    INDEX
    Explanations

    codes and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     analogies
    0.70
     juguete
    0.64
     belirli
    0.59
     increíble
    0.58
     eager
    0.57
    톈
    0.57
     twists
    0.56
     ludzi
    0.56
     llamada
    0.55
     aika
    0.55
    POSITIVE LOGITS
    XX
    0.88
    E
    0.86
    AL
    0.85
    0
    0.83
    UK
    0.83
    XV
    0.82
    1
    0.82
    AG
    0.81
    Q
    0.81
    US
    0.81
    Activations Density 0.112%

    No Known Activations