© 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-16K
    7. 1089
    Prev
    Next
    INDEX
    Explanations

    starting a game or roleplay

    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_16k_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
     compaction
    1.09
    argmin
    0.95
     benzoic
    0.94
     quercetin
    0.90
     McKinsey
    0.90
     Unilever
    0.89
    📊
    0.86
     mannitol
    0.86
    ⛳
    0.85
     biomarker
    0.84
    POSITIVE LOGITS
     fantasy
    2.06
     Fantasy
    1.86
    Fantasy
    1.74
     fantasies
    1.70
     Characters
    1.69
     personnage
    1.67
     characters
    1.65
     gameplay
    1.63
     fictional
    1.63
     adventures
    1.61
    Activations Density 3.067%

    No Known Activations