© 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-IT
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10144
    Prev
    Next
    INDEX
    Explanations

    purposeful and structured

    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_16k_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
    猊
    0.41
     물리
    0.40
    ው
    0.40
     ideals
    0.38
     indicators
    0.38
    Sud
    0.37
     ದ
    0.37
    ូច
    0.37
     jackpot
    0.37
     Últ
    0.37
    POSITIVE LOGITS
     purposely
    1.01
     deliberately
    0.99
     intentionally
    0.99
     purposefully
    0.93
     controlled
    0.87
     deliberate
    0.80
    Controlled
    0.78
    controlled
    0.77
     intentional
    0.76
     Controlled
    0.72
    Activations Density 0.170%

    No Known Activations