© 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. 41246
    Prev
    Next
    INDEX
    Explanations

    breakdown of explanations

    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
    ™,
    0.61
    ®,
    0.55
    !),
    0.55
    ––
    0.47
    ®.
    0.46
    !”,
    0.45
     zwycię
    0.45
     PlayStation
    0.45
     Pokémon
    0.44
     LEGO
    0.44
    POSITIVE LOGITS
     পুর্ব
    0.66
    ھ
    0.65
    postion
    0.64
    ੲ
    0.64
     नही
    0.63
    떄
    0.62
     upto
    0.61
     ,
    0.61
     কারনে
    0.61
    썻
    0.58
    Activations Density 0.141%

    No Known Activations