© 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. 3972
    Prev
    Next
    INDEX
    Explanations

    generate content

    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
     fourth
    1.21
     CCC
    1.20
     DMC
    1.17
    DCT
    1.15
    Fourth
    1.14
     DCT
    1.12
    ۴
    1.11
     divertido
    1.10
    tad
    1.10
    CCC
    1.10
    POSITIVE LOGITS
    Re
    0.78
     Re
    0.72
    Pa
    0.64
     Pa
    0.64
     Rem
    0.61
    Z
    0.61
     Rens
    0.61
    Net
    0.60
     Z
    0.59
     En
    0.59
    Activations Density 0.000%

    No Known Activations