© 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. 31-GEMMASCOPE-2-RES-262K
    7. 29620
    Prev
    Next
    INDEX
    Explanations

    specifies or signifies

    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_31_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
     Includes
    0.49
     cameos
    0.45
     eind
    0.44
     also
    0.44
     galvanized
    0.43
     preocup
    0.43
     {:
    0.42
     ugg
    0.42
     emphasize
    0.42
     {:.
    0.41
    POSITIVE LOGITS
    थर
    0.45
     tâche
    0.43
    త్మిక
    0.43
     kimia
    0.42
    תה
    0.41
     contagion
    0.41
    КИ
    0.41
    语文
    0.41
     langue
    0.40
    нул
    0.40
    Activations Density 0.000%

    No Known Activations