Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 6497
    Prev
    Next
    INDEX
    Explanations

    listing specific concepts

    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
    ക്കുകയും
    0.34
    wright
    0.33
    tragung
    0.33
    {}
    0.32
    Მ
    0.32
     ব্যাব
    0.32
    regation
    0.32
    ৃহে
    0.31
    Შ
    0.31
    厰
    0.31
    POSITIVE LOGITS
    :
    0.73
     yakni
    0.72
     yaitu
    0.71
    :
    0.70
     iaitu
    0.68
     —
    0.61
     –
    0.60
     czyli
    0.59
     :
    0.58
    *:
    0.58
    Activations Density 0.632%

    No Known Activations