© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 9026
    Prev
    Next
    INDEX
    Explanations

    sadness sad farewell

    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
    นี
    1.38
     inférieurs
    1.38
     continents
    1.37
     tubercles
    1.37
     chopsticks
    1.36
     fists
    1.34
     écriv
    1.31
    i
    1.31
    يير
    1.30
     bullies
    1.29
    POSITIVE LOGITS
    vedad
    1.68
    erweise
    1.66
    bones
    1.45
    cted
    1.43
    자에
    1.40
     놓고
    1.40
    theless
    1.38
    cessor
    1.37
    て
    1.36
    вая
    1.35
    Activations Density 0.036%

    No Known Activations