© 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. 3982
    Prev
    Next
    INDEX
    Explanations

    previous sentence intent

    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
     сли
    1.87
    possibleTypes
    1.82
    мина
    1.76
    าก
    1.71
    ιδ
    1.71
    ã
    1.71
    בת
    1.70
    urez
    1.70
    لال
    1.68
    맥
    1.67
    POSITIVE LOGITS
     land
    1.20
     We
    1.12
    桩
    1.08
     Here
    1.04
     means
    1.04
     I
    1.02
    肥料
    1.01
    袱
    1.01
     world
    1.00
     holds
    1.00
    Activations Density 0.000%

    No Known Activations