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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 111688
    Prev
    Next
    INDEX
    Explanations

    signal experience collect avoid track

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ቦ
    0.41
    ዣ
    0.40
    Avro
    0.39
     Bor
    0.38
     Justin
    0.38
     Wind
    0.37
     Metallica
    0.37
     Virginia
    0.37
     hasn
    0.36
    Wind
    0.36
    POSITIVE LOGITS
    裄
    0.42
     preferencias
    0.42
    केंद्र
    0.41
     referencias
    0.38
    partial
    0.38
     parcial
    0.38
     capacidades
    0.37
     preferências
    0.37
    कक्ष
    0.37
    ^{(
    0.36
    Activations Density 0.001%

    No Known Activations