© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 3251
    Prev
    Next
    INDEX
    Explanations

    in order, provided context

    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
    :
    1.10
    夫妇
    1.01
     is
    0.96
     (@
    0.87
     déi
    0.85
    atiya
    0.85
    は
    0.83
    }):=\
    0.81
     (
    0.79
    에는
    0.79
    POSITIVE LOGITS
    rinsic
    1.62
    FormProvider
    1.58
    AssetsResponse
    1.58
     repet
    1.57
     CRI
    1.55
    <end_of_image>
    1.55
     Cosmo
    1.54
     силу
    1.53
     lugar
    1.51
    AndroidResource
    1.49
    Activations Density 0.315%

    No Known Activations