© 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. 3814
    Prev
    Next
    INDEX
    Explanations

    internet search

    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
     Кы
    0.86
     soziale
    0.67
     início
    0.66
    葦
    0.61
    нару
    0.60
    σκευ
    0.60
     silk
    0.60
     else
    0.59
     zacz
    0.59
    9
    0.58
    POSITIVE LOGITS
    lens
    1.92
     πληροφο
    1.86
     currentDate
    1.80
    elens
    1.76
    ankton
    1.74
     คง
    1.72
    Exponent
    1.72
    녈
    1.71
    KURZBESCHREIBUNG
    1.70
     funders
    1.70
    Activations Density 0.017%

    No Known Activations