© 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. 16284
    Prev
    Next
    INDEX
    Explanations

    explain characteristics

    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
    attitude
    0.65
     কিংবা
    0.62
    Touchable
    0.59
     Klassen
    0.59
    словия
    0.58
    🌗
    0.57
     Classes
    0.56
    ermen
    0.55
    পরিব
    0.55
    +/-
    0.55
    POSITIVE LOGITS
     impenetrable
    0.65
    ד
    0.64
     destroyed
    0.63
    امر
    0.62
    اموش
    0.62
     prized
    0.62
     θέση
    0.62
     الأس
    0.61
     ornamented
    0.61
    წი
    0.61
    Activations Density 0.000%

    No Known Activations