© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 120228
    Prev
    Next
    INDEX
    Explanations

    profiles

    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
     boyut
    0.41
    produk
    0.41
    팸
    0.40
     introducción
    0.39
     supernat
    0.39
    buah
    0.38
    ুরে
    0.38
     आशी
    0.37
    ebu
    0.37
     संवेदनशील
    0.37
    POSITIVE LOGITS
    profiles
    0.50
     profiles
    0.48
     社
    0.43
     Profiles
    0.43
    Profiles
    0.43
     margin
    0.41
     PROFILE
    0.41
     profile
    0.40
    ProfileAction
    0.40
     Profile
    0.39
    Activations Density 0.002%

    No Known Activations