Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 3435
    Prev
    Next
    INDEX
    Explanations

    fantasy and imagination

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

    references to fantasy, imagination, and fictional or hypothetical scenarios (including dreams and role-play contexts).

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
    👍
    0.45
     👍
    0.41
    敨
    0.40
     रावत
    0.40
    asures
    0.39
    чеб
    0.39
    観察
    0.38
    ivatives
    0.38
    喈
    0.37
    jmath
    0.37
    POSITIVE LOGITS
     fantasy
    1.26
     fantasies
    1.18
     dream
    1.16
     fictional
    1.13
     imaginary
    1.11
     fantastical
    1.09
     काल्पनिक
    1.07
     imagination
    1.05
     fantas
    1.05
     dreamed
    1.02
    Activations Density 0.345%

    No Known Activations