© 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. 12-GEMMASCOPE-2-RES-262K
    7. 4980
    Prev
    Next
    INDEX
    Explanations

    n choose k

    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_12_width_262k_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
     lesiones
    1.13
    /-}$
    1.03
     êtes
    1.01
    ี
    0.99
     mjest
    0.96
     aula
    0.95
     supernatants
    0.95
     étape
    0.94
    ి
    0.93
     fibroblasts
    0.92
    POSITIVE LOGITS
    ed
    1.05
    يف
    0.96
    НА
    0.91
    ón
    0.88
    며
    0.84
    СК
    0.82
     отказа
    0.80
    at
    0.80
     अनुसंधान
    0.79
     لهذه
    0.79
    Activations Density 0.001%

    No Known Activations