© 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-16K
    7. 1810
    Prev
    Next
    INDEX
    Explanations

    list separators and specific topics

    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_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
    <unused820>
    2.99
    <unused1240>
    2.94
    <unused1563>
    2.81
    <unused852>
    2.77
     localVarAccept
    2.70
    <unused1468>
    2.69
    dcsset
    2.69
    clientsdetails
    2.66
    <unused848>
    2.65
    <unused1215>
    2.64
    POSITIVE LOGITS
     B
    1.55
     S
    1.41
     H
    1.31
     Dis
    1.28
     En
    1.28
     A
    1.28
     L
    1.26
     T
    1.23
     M
    1.22
     As
    1.21
    Activations Density 0.619%

    No Known Activations