© 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. 7122
    Prev
    Next
    INDEX
    Explanations

    pronouns and "party"

    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
     ourselves
    0.44
     unserem
    0.41
     нашим
    0.40
    limb
    0.39
    Mob
    0.39
    ت
    0.38
    ’
    0.37
    Sam
    0.37
    Partners
    0.37
     дальнейшем
    0.36
    POSITIVE LOGITS
     имеют
    0.48
    詬
    0.46
     condesc
    0.45
     хотят
    0.45
    कई
    0.45
     údaj
    0.45
    不允许
    0.45
     яку
    0.44
     virulent
    0.44
    莫名
    0.43
    Activations Density 0.026%

    No Known Activations