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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 12962
    Prev
    Next
    INDEX
    Explanations

    URL mapping configuration file

    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_65k_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
     */
    0.46
     deprived
    0.42
     unauthorized
    0.40
     undocumented
    0.39
     grievous
    0.38
     misguided
    0.37
     endangered
    0.37
     undue
    0.37
     historical
    0.36
     /**
    0.36
    POSITIVE LOGITS
    Django
    0.43
     configuração
    0.43
    django
    0.43
    Pics
    0.43
    matplotlib
    0.43
    Wave
    0.42
    Ubuntu
    0.42
    acuda
    0.42
    Modular
    0.42
    Connection
    0.40
    Activations Density 0.002%

    No Known Activations