© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8881
    Prev
    Next
    INDEX
    Explanations

    numbered lists

    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
    Third
    0.71
    第三
    0.64
    Existing
    0.62
    $`
    0.60
        
    0.59
    Really
    0.58
    Person
    0.57
    Role
    0.57
     Third
    0.57
               
    0.56
    POSITIVE LOGITS
    ៕
    0.67
     ladle
    0.65
     jubil
    0.64
     nhé
    0.64
    icolored
    0.64
     jdk
    0.63
    angk
    0.61
     codef
    0.61
     debugger
    0.61
     magenta
    0.61
    Activations Density 0.062%

    No Known Activations