© 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
    5. 40-GEMMASCOPE-2-RES-16K
    7. 9822
    Prev
    Next
    INDEX
    Explanations

    affordability and budget constraints

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

    risk tolerance and budget available

    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
     improperly
    0.43
    subsetneq
    0.40
     숨
    0.36
    rā
    0.35
    adim
    0.35
    鸚
    0.35
    タイ
    0.34
     ಯ
    0.34
     доби
    0.34
     треба
    0.33
    POSITIVE LOGITS
     afford
    1.40
     affording
    1.23
     afforded
    1.04
     affords
    1.01
     affordability
    0.97
     budget
    0.95
    予算
    0.92
    余裕
    0.91
    budget
    0.89
     affordable
    0.89
    Activations Density 0.505%

    No Known Activations