© 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. 21820
    Prev
    Next
    INDEX
    Explanations

    further

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

    interesting questions

    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
    those
    0.54
    consuming
    0.47
     preoccupation
    0.47
    injury
    0.46
    persons
    0.46
    typical
    0.45
    theoretical
    0.45
    갇
    0.45
     delinquency
    0.44
    masters
    0.44
    POSITIVE LOGITS
     further
    0.66
    进一步
    0.59
     Further
    0.55
     дальней
    0.55
     weitere
    0.54
    继续
    0.54
     Weitere
    0.52
     dalje
    0.52
     melhorar
    0.52
     további
    0.51
    Activations Density 0.000%

    No Known Activations