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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 4065
    Prev
    Next
    INDEX
    Explanations

    emphasizing adverbs like really, exactly

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

    intensifier + descriptive phrase

    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
     केलेले
    0.39
    kem
    0.39
    𝒓
    0.38
    ularity
    0.38
    érences
    0.37
    uité
    0.35
    రుపు
    0.35
    Kerry
    0.35
     connections
    0.34
    邵
    0.34
    POSITIVE LOGITS
     speaking
    0.55
    speaking
    0.50
     understood
    0.49
     importantly
    0.46
     frankly
    0.45
     hablando
    0.45
     taxed
    0.44
    Speaking
    0.44
    weds
    0.44
    യില്ല
    0.42
    Activations Density 0.099%

    No Known Activations