© 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. 141373
    Prev
    Next
    INDEX
    Explanations

    parts or training

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

    predict astronomical events

    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
    mlp
    0.57
     விழுப்பு
    0.52
    全新
    0.50
     திரைப்படம்
    0.50
    犒
    0.50
    חד
    0.50
    ▥
    0.48
     חד
    0.47
    మ్యాచ్
    0.47
    inspir
    0.47
    POSITIVE LOGITS
     get
    0.65
     but
    0.51
     little
    0.49
     tetapi
    0.47
     pero
    0.46
     physically
    0.44
    get
    0.44
    1
    0.44
     be
    0.44
     have
    0.44
    Activations Density 0.001%

    No Known Activations