© 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. 45518
    Prev
    Next
    INDEX
    Explanations

    company. For all

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

    strengths, relationships, enforcement

    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
     funcionando
    0.44
    నీ
    0.43
     handful
    0.41
    5
    0.40
    から
    0.39
     neat
    0.39
     solución
    0.39
     aiut
    0.39
    牛
    0.39
    キュ
    0.38
    POSITIVE LOGITS
     उत्सव
    0.52
     ponctués
    0.50
     प्रेजेंट
    0.47
    म्प्ट
    0.47
     दिवस
    0.46
    ोत्सव
    0.46
     चैलेंज
    0.46
     introns
    0.46
     التلاميذ
    0.45
     презен
    0.45
    Activations Density 0.000%

    No Known Activations