© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 1395
    Prev
    Next
    INDEX
    Explanations

    protagonist's role and narrative elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_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
    Config
    0.99
     Breite
    0.92
    softmax
    0.91
    }_{
    0.89
    엊
    0.88
    Output
    0.88
    ktops
    0.87
    input
    0.85
    inline
    0.85
    🔈
    0.85
    POSITIVE LOGITS
     protagonist
    2.05
     mysterious
    1.83
     protagonists
    1.77
     personnages
    1.75
     venge
    1.75
     flashbacks
    1.74
     supernatural
    1.72
     betrayal
    1.68
     sinister
    1.65
     personaggi
    1.62
    Activations Density 1.016%

    No Known Activations