© 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-262K
    7. 71513
    Prev
    Next
    INDEX
    Explanations

    jeans, attackers, GameObject, Russian, Greek, numbers

    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_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
    У
    0.44
    ታዊ
    0.40
    Grupo
    0.39
    투
    0.38
    Ю
    0.38
    ரும
    0.37
    Е
    0.37
     Боль
    0.37
    А
    0.36
    포
    0.36
    POSITIVE LOGITS
     اُن
    0.47
     δύο
    0.44
     speculators
    0.42
     constitutes
    0.41
     χρη
    0.39
     создает
    0.39
     affords
    0.39
     gives
    0.39
     puts
    0.38
     ushered
    0.38
    Activations Density 0.000%

    No Known Activations