© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 3632
    Prev
    Next
    INDEX
    Explanations

    smooth as polished marble

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
    es
    1.82
    en
    1.74
    ej
    1.62
    et
    1.52
    eing
    1.51
    e
    1.50
    o
    1.43
    ed
    1.43
    ek
    1.39
    eb
    1.39
    POSITIVE LOGITS
     الفلسط
    2.18
    ̥
    2.14
    anean
    2.13
    space
    2.12
     subsurface
    2.08
    candy
    2.08
    ificial
    2.07
    <unused1691>
    2.07
     atmosfera
    2.06
    Metallic
    2.05
    Activations Density 0.100%

    No Known Activations