© 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. 56972
    Prev
    Next
    INDEX
    Explanations

    implies a

    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
     pouvaient
    0.43
    菊
    0.41
    benef
    0.40
     payloads
    0.40
    mAvailable
    0.39
     benefitting
    0.39
     ilyen
    0.39
    に近い
    0.39
    運
    0.39
     benefited
    0.39
    POSITIVE LOGITS
     magazines
    0.44
     वाई
    0.42
     controvers
    0.42
     UFO
    0.42
     defectos
    0.42
     revistas
    0.41
     التمرين
    0.41
     barren
    0.41
     wrongful
    0.41
     instants
    0.40
    Activations Density 0.016%

    No Known Activations