© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 370
    Prev
    Next
    INDEX
    Explanations

    modifying or adapting systems

    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_31_width_16k_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
     is
    0.17
    matic
    0.16
     ಯಾವಾಗ
    0.16
     ふ
    0.15
    odos
    0.15
     subfamily
    0.15
    degree
    0.15
     {
    0.14
     phrase
    0.14
    mselves
    0.14
    POSITIVE LOGITS
     the
    0.24
     τις
    0.20
     theſe
    0.20
     свои
    0.19
     svoje
    0.19
     them
    0.18
     stvari
    0.18
     our
    0.18
    而来
    0.18
     svůj
    0.18
    Activations Density 3.771%

    No Known Activations