© 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. 72114
    Prev
    Next
    INDEX
    Explanations

    images, photos, buy, sessions, designers

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

    The

    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
     residencial
    0.47
     aliquot
    0.45
     পরেই
    0.43
     週
    0.43
     invariant
    0.43
     EMPC
    0.42
     typology
    0.41
     homogenization
    0.41
     kalimat
    0.41
     mondiale
    0.40
    POSITIVE LOGITS
    鐟
    0.49
    oarece
    0.47
     yüzden
    0.45
    ặc
    0.45
    चुअल
    0.44
    anlı
    0.44
    laşı
    0.43
    меся
    0.42
    ग्राहक
    0.42
    לא
    0.42
    Activations Density 0.000%

    No Known Activations