© 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-262K
    7. 41169
    Prev
    Next
    INDEX
    Explanations

    future building

    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_262k_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
     amateurs
    0.49
     dozen
    0.47
     Fris
    0.45
     amateur
    0.44
     anyway
    0.43
     a
    0.43
     backstage
    0.43
     guerr
    0.43
     loosen
    0.42
    Doch
    0.42
    POSITIVE LOGITS
    未來
    0.52
    未来
    0.50
     разрабаты
    0.48
    籶
    0.48
    向けの
    0.46
     буду
    0.45
    راحی
    0.45
     будущем
    0.45
     futuras
    0.44
    सभा
    0.42
    Activations Density 0.005%

    No Known Activations