© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-65K
    7. 1104
    Prev
    Next
    INDEX
    Explanations

    specific/certain frameworks, projects, or circumstances

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_65k_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
     व्‍य
    0.66
    <unused2126>
    0.62
    odi
    0.61
     useNavigate
    0.59
    ުގައި
    0.59
    வையை
    0.58
     sympathique
    0.58
    <unused2164>
    0.58
     sizlere
    0.58
    nw
    0.57
    POSITIVE LOGITS
     specific
    1.05
     특정
    0.97
    Specific
    0.95
     Specific
    0.89
     specifics
    0.87
    specific
    0.87
     Certain
    0.85
    Specifically
    0.84
    Certain
    0.83
     specifically
    0.83
    Activations Density 0.975%

    No Known Activations