© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 7092
    Prev
    Next
    INDEX
    Explanations

    reporting verbs in dialogue

    np_acts-logits-general · gemini-2.5-flash-lite

    voice quality descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     saying
    1.00
     berkata
    0.80
     dizendo
    0.79
     Saying
    0.78
     mengatakan
    0.76
     diciendo
    0.75
    say
    0.69
    说
    0.69
    说道
    0.68
     قائ
    0.68
    POSITIVE LOGITS
     putting
    0.47
     jumping
    0.47
     Jumping
    0.45
     তুলতে
    0.44
     entrando
    0.43
    रियर
    0.41
    jumping
    0.41
    Putting
    0.41
     달려
    0.41
     পাচ্ছি
    0.40
    Activations Density 0.010%

    No Known Activations