© 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. 88621
    Prev
    Next
    INDEX
    Explanations

    financial transactions and information

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

    exploratory investigation dialogue

    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
    inians
    0.50
    anns
    0.47
    ]={"
    0.47
     ধারাবাহ
    0.44
    IPP
    0.44
     बिलियन
    0.44
     Bulls
    0.44
    igram
    0.44
     drawed
    0.43
    erit
    0.43
    POSITIVE LOGITS
     recharging
    0.50
    면에
    0.48
    ツ
    0.47
    バ
    0.46
    タ
    0.46
     Fiona
    0.45
    ながら
    0.44
     Charlene
    0.43
    ایی
    0.43
     ინფორმა
    0.43
    Activations Density 0.001%

    No Known Activations