© 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. 51103
    Prev
    Next
    INDEX
    Explanations

    Les Miserables title

    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
     and
    0.67
    _
    0.53
     Barrett
    0.49
     Neu
    0.47
     St
    0.47
     Ac
    0.45
     Barr
    0.45
     Dum
    0.45
     Yosemite
    0.45
     And
    0.44
    POSITIVE LOGITS
    avaliacao
    0.55
    参加
    0.55
    ເພດ
    0.54
    ᓲ
    0.53
    õe
    0.51
    多様
    0.51
     твор
    0.49
     प्रयत्न
    0.49
     выполнять
    0.49
    োর্টের
    0.49
    Activations Density 0.002%

    No Known Activations