© 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. 7723
    Prev
    Next
    INDEX
    Explanations

    equations, formulas, calculations

    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
    Ruby
    0.63
    Jade
    0.58
    ADY
    0.55
    𓏸
    0.52
    ಲಾ
    0.51
    昕
    0.51
    Utah
    0.51
    락
    0.51
    lick
    0.50
    erry
    0.50
    POSITIVE LOGITS
     maize
    0.66
     pommes
    0.62
     ejaculation
    0.61
     wares
    0.58
     according
    0.55
     Inverse
    0.55
     volgens
    0.55
     calcareous
    0.55
     propylene
    0.54
     cornea
    0.53
    Activations Density 0.000%

    No Known Activations