© 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. 51699
    Prev
    Next
    INDEX
    Explanations

    first followed by enumeration

    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
     similar
    0.39
     resist
    0.39
    ]}{
    0.37
    arounds
    0.36
     semelhantes
    0.36
     비슷
    0.36
    하거나
    0.36
    得知
    0.36
    几十
    0.36
    或
    0.36
    POSITIVE LOGITS
     instalment
    0.70
     installment
    0.66
     annual
    0.63
    installment
    0.62
    annual
    0.60
     Annual
    0.54
     anual
    0.52
     officielle
    0.52
     annualized
    0.51
    Annual
    0.50
    Activations Density 0.035%

    No Known Activations