© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-262K
    7. 5359
    Prev
    Next
    INDEX
    Explanations

    types of information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_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
     other
    0.37
      
    0.37
     Microsoft
    0.37
    その他の
    0.37
     Transportation
    0.34
    Managing
    0.34
    Other
    0.32
    ఈ
    0.31
    Microsoft
    0.31
     Sonder
    0.31
    POSITIVE LOGITS
     doesn
    0.59
     could
    0.56
     musí
    0.55
     must
    0.54
     gets
    0.54
     goes
    0.53
     viene
    0.52
     prevails
    0.52
     gives
    0.51
     будет
    0.51
    Activations Density 0.226%

    No Known Activations