© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 149836
    Prev
    Next
    INDEX
    Explanations

    prices after 'for' or 'just'

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

    for prices or fees

    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_31_width_262k_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
     Permissions
    0.40
    EndInit
    0.39
     //</
    0.39
    ᵗ
    0.38
    ಷ್ಟ
    0.38
     permissions
    0.37
    tà
    0.37
    溼
    0.37
     Reduction
    0.37
    𝕠
    0.36
    POSITIVE LOGITS
     $
    0.98
     $\$
    0.96
     €
    0.83
     $€
    0.81
     £
    0.80
     ₹
    0.75
     ~$
    0.72
     ₽
    0.72
     $.
    0.71
    $\$
    0.71
    Activations Density 0.088%

    No Known Activations