© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 84312
    Prev
    Next
    INDEX
    Explanations

    predicting futuredriving listeners

    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
     Ayuntamiento
    0.46
    你想
    0.44
    Archivo
    0.43
    説明
    0.42
     कैप्शन
    0.42
     Agustín
    0.42
     Verónica
    0.42
    æ
    0.41
    命令
    0.40
     primero
    0.40
    POSITIVE LOGITS
     welds
    0.49
     guitars
    0.48
     hulls
    0.48
     guitarist
    0.48
     berths
    0.47
     golfers
    0.47
     rigs
    0.45
     swimmers
    0.45
     intermediates
    0.44
     eagles
    0.44
    Activations Density 0.005%

    No Known Activations