© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10239
    Prev
    Next
    INDEX
    Explanations

    according to/in accordance with

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

    quality descriptions and item states

    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_40_width_16k_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
     Costco
    0.61
    accessories
    0.60
    expensive
    0.59
    店
    0.59
     expensive
    0.58
     variedad
    0.57
    店内
    0.57
    最好的
    0.57
    新款
    0.57
     구입
    0.57
    POSITIVE LOGITS
     цело
    0.47
     conformément
    0.44
    Organizations
    0.44
     مطابق
    0.43
    াবাদ
    0.42
    題目
    0.42
     gemäß
    0.42
     }];
    0.42
     РАН
    0.41
    युद्ध
    0.41
    Activations Density 0.125%

    No Known Activations