© 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. 4946
    Prev
    Next
    INDEX
    Explanations

    seeking practical suggestions

    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
     calendário
    1.45
    Explanation
    1.39
     gebruikt
    1.38
     alternates
    1.38
     Kenyon
    1.38
    Ɔ
    1.37
    다라고
    1.32
     たり
    1.31
     多い
    1.31
    ioane
    1.31
    POSITIVE LOGITS
     a
    1.65
    颯
    1.48
     your
    1.44
     primordial
    1.41
    心中的
    1.40
     primal
    1.37
    ib
    1.35
     hos
    1.32
     blissful
    1.32
     một
    1.32
    Activations Density 0.033%

    No Known Activations