© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5047
    Prev
    Next
    INDEX
    Explanations

    progress or distance

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

    further

    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_53_width_65k_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
    द्दीन
    0.35
    LensFlare
    0.34
     তেমনি
    0.33
    鏻
    0.33
    ⓓ
    0.32
     moins
    0.32
    raison
    0.31
    绰
    0.31
    역시
    0.31
    Oreal
    0.31
    POSITIVE LOGITS
     further
    5.31
    further
    5.03
    Further
    4.66
     Further
    4.63
    进一步
    4.59
     FURTHER
    4.44
     дальней
    4.03
     дальше
    3.91
     farther
    3.75
    さらに
    3.67
    Activations Density 0.462%

    No Known Activations