© 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. 40-GEMMASCOPE-2-RES-65K
    7. 48587
    Prev
    Next
    INDEX
    Explanations

    spring training baseball

    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_65k_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
     بچ
    0.42
     cilind
    0.41
     चैप्टर्स
    0.40
     цилинд
    0.40
     Eisen
    0.38
     искусство
    0.37
    ▣
    0.37
    ፊ
    0.37
     बहुपद
    0.37
     बच्ची
    0.36
    POSITIVE LOGITS
    ву
    0.44
     showcase
    0.40
    voje
    0.38
     resumption
    0.37
     rookies
    0.37
     Prospects
    0.37
     Showcase
    0.36
    oL
    0.36
     fréquente
    0.36
     সংকো
    0.36
    Activations Density 0.006%

    No Known Activations