© 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. 3131
    Prev
    Next
    INDEX
    Explanations

    leaving behind or in

    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
     now
    0.52
     clearly
    0.43
    ческом
    0.43
    ORI
    0.43
     commercially
    0.43
    ń
    0.42
     ribs
    0.42
     push
    0.41
    含量
    0.41
     behavi
    0.41
    POSITIVE LOGITS
     jogadores
    0.53
    naz
    0.52
    一顆
    0.52
     క
    0.50
     питання
    0.49
     hráč
    0.49
     Cens
    0.49
    rukt
    0.49
     Taschen
    0.48
     पोस्टर
    0.47
    Activations Density 0.001%

    No Known Activations