© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15473
    Prev
    Next
    INDEX
    Explanations

    opposite arm and leg

    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
    ificates
    0.84
    aman
    0.82
    }$}
    0.80
    Smooth
    0.80
    çok
    0.77
    ()
    0.75
    Vent
    0.75
    ').':
    0.74
    屍
    0.73
    arni
    0.73
    POSITIVE LOGITS
     folding
    0.80
     idyllic
    0.77
     algorithmic
    0.71
     flawed
    0.68
     conversation
    0.68
     fictional
    0.68
     reckoning
    0.67
     workday
    0.66
     inning
    0.66
     measurable
    0.66
    Activations Density 0.001%

    No Known Activations