© 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. 1749
    Prev
    Next
    INDEX
    Explanations

    non- or brace or STRENGTH or No

    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
     mediana
    0.50
     complainants
    0.47
    ︵
    0.43
    🏬
    0.43
     vengo
    0.42
    ✐
    0.42
     shutterstock
    0.42
     masculina
    0.42
     allegedly
    0.41
     diduga
    0.41
    POSITIVE LOGITS
    0
    0.45
     Auswahl
    0.45
     kritis
    0.44
     rač
    0.44
    ıp
    0.43
     對
    0.43
     સર્
    0.43
     surrog
    0.42
    undos
    0.42
     карбо
    0.42
    Activations Density 0.000%

    No Known Activations