© 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. 3746
    Prev
    Next
    INDEX
    Explanations

    conditional clauses and outcomes

    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
     terminology
    0.46
    rightsquigarrow
    0.46
     chit
    0.45
     ATLAS
    0.44
     internasional
    0.43
     ম
    0.43
     esports
    0.43
    .
    0.43
     cuestiones
    0.42
     preparing
    0.41
    POSITIVE LOGITS
     عندما
    0.91
     wenn
    0.89
    只要
    0.84
     dacă
    0.84
     when
    0.82
    如果
    0.82
     gdy
    0.82
     если
    0.81
    если
    0.80
    当
    0.80
    Activations Density 0.028%

    No Known Activations