© 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. 31-GEMMASCOPE-2-RES-262K
    7. 42122
    Prev
    Next
    INDEX
    Explanations

    years and dates

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

    DNA to RNA to protein

    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
     alerting
    0.50
     ApiException
    0.47
     কর্মকর্ত
    0.43
     開始
    0.43
     apiKey
    0.42
     uitgenodigd
    0.42
    щика
    0.42
    놁
    0.42
     alerted
    0.42
     oxidant
    0.42
    POSITIVE LOGITS
    ،
    0.53
    ğı
    0.44
    IDADE
    0.44
    ursal
    0.43
     famiglia
    0.43
    idad
    0.43
    sak
    0.42
     diva
    0.42
    mios
    0.42
     palazzo
    0.42
    Activations Density 0.000%

    No Known Activations