© 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. 12-GEMMASCOPE-2-RES-262K
    7. 36189
    Prev
    Next
    INDEX
    Explanations

    while followed by a clause describing a state or action

    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_12_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
    д
    1.30
    ков
    1.21
    ιτε
    1.20
     번째
    1.18
    り
    1.17
     lồ
    1.16
    ה
    1.15
    ées
    1.13
    восто
    1.13
    і
    1.11
    POSITIVE LOGITS
    cia
    1.81
    c
    1.80
    b
    1.62
    ca
    1.59
    ع
    1.52
    cía
    1.46
    brak
    1.39
    cí
    1.37
    cose
    1.37
    cích
    1.37
    Activations Density 0.007%

    No Known Activations