© 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-262K
    7. 26709
    Prev
    Next
    INDEX
    Explanations

    screams shouts yells

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

    loud vocalizations of distress

    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_262k_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
    😌
    0.54
    ியது
    0.53
     твор
    0.52
     वीडियो
    0.50
     кок
    0.49
    entretien
    0.49
     पुष्
    0.48
    electro
    0.48
    🫤
    0.48
     অংশ
    0.47
    POSITIVE LOGITS
     screaming
    1.06
     loudly
    1.05
     screamed
    1.02
     shout
    1.01
     shouted
    1.00
     scream
    0.96
     screams
    0.94
     yelling
    0.93
     shouting
    0.93
     yelled
    0.93
    Activations Density 0.049%

    No Known Activations