© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 189441
    Prev
    Next
    INDEX
    Explanations

    based on

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

    expulsion or removal

    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
    Not in Any Lists

    No Comments

    Negative Logits
    彪
    0.51
    down
    0.49
    Gauche
    0.47
    ima
    0.43
     quedaría
    0.42
    PLF
    0.41
    níku
    0.41
     हूँ
    0.41
    澹
    0.41
    ক্ত
    0.41
    POSITIVE LOGITS
     ท
    0.56
     את
    0.51
     기준
    0.50
     Monica
    0.50
     impose
    0.49
     Thiết
    0.49
     imposes
    0.48
     kız
    0.48
    脌
    0.48
    기준
    0.47
    Activations Density 0.000%

    No Known Activations