© 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. 176967
    Prev
    Next
    INDEX
    Explanations

    case for, big and, short of

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

    specific lists and classifications

    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
     стаўкі
    0.58
    ablement
    0.51
     फाटक
    0.50
    坩
    0.49
     broadcasters
    0.49
    iędzy
    0.48
     সেতু
    0.48
    냇
    0.48
    ப்பட்டுள்ள
    0.47
     comité
    0.47
    POSITIVE LOGITS
     Plugin
    0.45
     alpha
    0.43
     compil
    0.42
     Username
    0.42
     nocturnal
    0.42
    sword
    0.41
     Beta
    0.40
     None
    0.40
     tumor
    0.40
     Often
    0.40
    Activations Density 0.001%

    No Known Activations