© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 75569
    Prev
    Next
    INDEX
    Explanations

    your mother jokes

    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_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
    運用
    0.40
    бавля
    0.40
    िपल
    0.38
     लौटने
    0.38
    妺
    0.37
     asas
    0.37
    фор
    0.36
     Autobi
    0.36
    渓
    0.36
     {},
    0.36
    POSITIVE LOGITS
     terakhir
    0.49
    h
    0.47
     অবশেষে
    0.47
     thậm
    0.44
    শেষ
    0.43
    ተኛ
    0.43
    ž
    0.43
     supremacy
    0.43
     finally
    0.43
    ån
    0.42
    Activations Density 0.006%

    No Known Activations