© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 47462
    Prev
    Next
    INDEX
    Explanations

    opportunity / temperature / machine / today / beautiful / atmosphere

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    idler
    0.43
    kit
    0.41
    idal
    0.41
    --
    0.40
    ravel
    0.39
    ids
    0.39
    iyal
    0.38
    agma
    0.36
    чина
    0.36
    adilla
    0.36
    POSITIVE LOGITS
     Oggi
    0.50
    ◤
    0.47
     అవకాశ
    0.44
     রাইফ
    0.44
    뻤
    0.43
     opportunità
    0.43
     broch
    0.42
     commemorate
    0.42
     hermosa
    0.42
     atmósfera
    0.42
    Activations Density 0.007%

    No Known Activations