© 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-16K
    7. 779
    Prev
    Next
    INDEX
    Explanations

    GPS coordinate, quantum dots, early-stage startup

    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_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    VM
    1.09
     Vox
    1.07
    vel
    1.06
    Vox
    1.01
    VG
    0.99
    VEL
    0.97
    Vid
    0.97
     VRS
    0.96
    V
    0.95
    VO
    0.95
    POSITIVE LOGITS
    asshi
    0.86
    ätte
    0.83
     Karlsruhe
    0.81
     Ebert
    0.77
     Arden
    0.76
     Oeste
    0.75
    Schneider
    0.75
     Arne
    0.75
     Schneider
    0.72
    әне
    0.72
    Activations Density 0.887%

    No Known Activations