© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 92266
    Prev
    Next
    INDEX
    Explanations

    vowed to insure

    np_acts-logits-general · gemini-2.5-flash-lite

    explain or mention details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     pessimistic
    0.44
    一线
    0.41
     dramatic
    0.40
     высокая
    0.40
     二
    0.39
    大大
    0.39
    ů
    0.39
    alar
    0.39
    oon
    0.38
    かなり
    0.38
    POSITIVE LOGITS
     შეიძლება
    0.45
    酐
    0.45
     ausgewählt
    0.44
     docentes
    0.42
     mā
    0.42
     Mā
    0.42
     Vertrag
    0.42
     SAB
    0.41
    gable
    0.41
    ijoje
    0.41
    Activations Density 0.000%

    No Known Activations