© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 91598
    Prev
    Next
    INDEX
    Explanations

    foreign language constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
     باز
    0.47
    自
    0.42
     stá
    0.42
     сов
    0.40
     заво
    0.39
     Jharkhand
    0.39
    нува
    0.39
     మే
    0.38
    hnt
    0.38
    再
    0.38
    POSITIVE LOGITS
    ſe
    0.51
     പോലുള്ള
    0.50
     pequeño
    0.47
    ന്റ്
    0.47
    ibrant
    0.46
     kože
    0.46
     tetapi
    0.45
    ட்ரோ
    0.45
     ஆனால்
    0.44
     antidepressant
    0.44
    Activations Density 0.004%

    No Known Activations