© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 99811
    Prev
    Next
    INDEX
    Explanations

    absurdist and unsettling descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_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
     kiddos
    0.58
     hubby
    0.55
     ибо
    0.52
     chibi
    0.50
     Awesome
    0.50
    😜
    0.50
     OMG
    0.49
     BFF
    0.48
    Karma
    0.48
     karma
    0.48
    POSITIVE LOGITS
     fucking
    0.43
     fuck
    0.39
     kinds
    0.37
     fucked
    0.36
     것처럼
    0.36
    –
    0.36
     fasc
    0.35
     aggressively
    0.35
    냐면
    0.35
     ceremonial
    0.35
    Activations Density 0.020%

    No Known Activations