© 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. 145795
    Prev
    Next
    INDEX
    Explanations

    settings, info, or signed documents

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

    tsundere roleplay prompts

    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
     KPSS
    0.43
     Discrimination
    0.41
    الس
    0.40
     বিষয়ের
    0.40
     النوع
    0.39
     voltage
    0.38
     Streptococcus
    0.38
    ░
    0.38
    燭
    0.38
     latitudine
    0.38
    POSITIVE LOGITS
     zal
    0.55
    américa
    0.47
     popularity
    0.46
     cuáles
    0.46
    wealth
    0.45
    zoni
    0.45
     countryside
    0.44
     لیګ
    0.44
     grail
    0.43
     centralized
    0.43
    Activations Density 0.000%

    No Known Activations