© 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. 4368
    Prev
    Next
    INDEX
    Explanations

    questions about well-being

    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
    你
    0.66
    ುದು
    0.63
    お待ち
    0.59
     is
    0.59
    靦
    0.57
     banter
    0.57
    覂
    0.56
    捚
    0.56
    <unused27>
    0.55
     informazioni
    0.55
    POSITIVE LOGITS
    .
    1.00
    r
    0.83
    1
    0.79
    2
    0.73
     that
    0.73
    3
    0.71
    ,
    0.69
    -
    0.69
    urs
    0.68
    !
    0.68
    Activations Density 0.834%

    No Known Activations