© 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-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 6523
    Prev
    Next
    INDEX
    Explanations

    that followed by a verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_width_16k_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
    锏
    0.82
     codice
    0.77
    কির
    0.75
    곡
    0.74
    Ко
    0.74
    的代码
    0.73
    તે
    0.73
     Skeleton
    0.73
    Ფ
    0.73
     स्की
    0.71
    POSITIVE LOGITS
     validating
    0.63
     validation
    0.62
    жала
    0.61
     Acceptance
    0.59
     acceptance
    0.59
     החד
    0.58
     validations
    0.58
     Validation
    0.57
    Accept
    0.57
     Accept
    0.56
    Activations Density 0.177%

    No Known Activations