© 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. 41-GEMMASCOPE-2-RES-65K
    7. 1506
    Prev
    Next
    INDEX
    Explanations

    archaic language

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_41_width_65k_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
     γιατί
    0.46
     prostu
    0.46
    ﮧ
    0.46
    ichever
    0.45
    குழந்த
    0.45
     পড়াশ
    0.44
    lında
    0.44
     batik
    0.43
     Arap
    0.43
    ቿ
    0.43
    POSITIVE LOGITS
     doth
    1.20
     hath
    1.05
     saith
    0.76
     aforesaid
    0.74
     yea
    0.71
     moſt
    0.70
     unto
    0.68
     whereof
    0.67
     sundry
    0.65
     shew
    0.64
    Activations Density 0.079%

    No Known Activations