© 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. 4922
    Prev
    Next
    INDEX
    Explanations

    canyons atmospheres absorbing crevices

    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
     This
    2.11
     The
    1.83
     And
    1.82
    This
    1.81
     With
    1.75
    .
    1.71
     Just
    1.70
     It
    1.69
     To
    1.66
     &
    1.66
    POSITIVE LOGITS
     atmospheres
    1.52
     vapors
    1.49
    奈川
    1.46
     stratosphere
    1.39
     nuclei
    1.36
     canyons
    1.36
     thermostats
    1.36
     absorbing
    1.35
     niches
    1.35
     crevices
    1.34
    Activations Density 0.111%

    No Known Activations