© 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. 3898
    Prev
    Next
    INDEX
    Explanations

    economic hardship

    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
     model
    0.95
     Model
    0.81
    igma
    0.80
    optimizer
    0.74
    ベーション
    0.72
    erm
    0.72
     M
    0.71
    M
    0.68
     administration
    0.67
     v
    0.66
    POSITIVE LOGITS
     sassy
    1.62
     RPS
    1.61
     Héctor
    1.58
    <unused505>
    1.58
    <unused907>
    1.57
    <unused1667>
    1.56
    ︰
    1.54
    <unused1960>
    1.53
    funny
    1.52
    <unused650>
    1.52
    Activations Density 0.083%

    No Known Activations