© 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-262K
    7. 221430
    Prev
    Next
    INDEX
    Explanations

    large dog

    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
     Divisions
    0.43
    惀
    0.42
    <unused369>
    0.42
     Protocols
    0.42
    ОВ
    0.40
    寶
    0.40
    设备
    0.39
     dwells
    0.39
    宝
    0.39
     그랬
    0.38
    POSITIVE LOGITS
     momentum
    0.44
     terrier
    0.43
    bellar
    0.42
     Allende
    0.38
     stain
    0.38
     commissioner
    0.37
     watery
    0.37
     town
    0.36
     personaje
    0.36
    iglio
    0.36
    Activations Density 0.006%

    No Known Activations