© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 4975
    Prev
    Next
    INDEX
    Explanations

    one step at a time

    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
    Negative Logits
     method
    1.39
     secrets
    1.37
    Method
    1.37
    Keyword
    1.32
     Ascot
    1.32
     krypt
    1.32
    BANK
    1.32
     bodyguard
    1.31
    꼽
    1.29
    method
    1.29
    POSITIVE LOGITS
     diálogo
    1.32
     compassion
    1.31
     dialogo
    1.29
     empathy
    1.27
     collaborative
    1.26
     convivencia
    1.25
     harmonious
    1.25
     empathetic
    1.24
     constructive
    1.24
     UNITY
    1.23
    Activations Density 0.270%

    No Known Activations