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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 13220
    Prev
    Next
    INDEX
    Explanations

    why don't 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_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
     ***
    0.45
     मानस
    0.42
    ***
    0.41
    𝟙
    0.38
    ැබ
    0.38
    reeting
    0.37
    **,
    0.37
    Topbar
    0.37
    oreal
    0.37
     *=
    0.36
    POSITIVE LOGITS
    деть
    0.40
     Alkali
    0.39
     област
    0.38
    াইড
    0.38
     FTE
    0.38
     stear
    0.38
     फ्ले
    0.37
    СТЕ
    0.37
    velles
    0.37
    rade
    0.37
    Activations Density 0.000%

    No Known Activations