© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12941
    Prev
    Next
    INDEX
    Explanations

    loud vocalizations and strong emotions

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

    exclamations and shouts

    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_31_width_16k_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
    🫤
    0.50
     insidious
    0.50
     ciek
    0.49
    😶
    0.48
    sneak
    0.47
    🤔
    0.47
    黯
    0.47
     crept
    0.46
     সীমিত
    0.46
    😌
    0.46
    POSITIVE LOGITS
     shouts
    1.22
     shout
    1.19
     shouted
    1.18
     shouting
    1.17
     yells
    1.13
     yelling
    1.12
     screaming
    1.11
     screamed
    1.08
     yelled
    1.05
     চিৎকার
    1.05
    Activations Density 0.394%

    No Known Activations