© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 3921
    Prev
    Next
    INDEX
    Explanations

    museum contents and artifacts

    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
     gobier
    0.52
     indiscriminate
    0.44
     abuso
    0.44
    overnment
    0.43
     wnios
    0.43
     indiscrimin
    0.42
    могою
    0.41
    𝗄
    0.41
     algorithmic
    0.40
     comorbid
    0.40
    POSITIVE LOGITS
     museum
    1.19
     Museum
    1.16
     exhibitions
    1.15
     exhibits
    1.06
     exhibit
    1.00
    Museum
    0.99
     exhibition
    0.96
     전시
    0.89
     музей
    0.87
     musée
    0.87
    Activations Density 0.022%

    No Known Activations