© 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. 8652
    Prev
    Next
    INDEX
    Explanations

    Google DeepMind consortium and family

    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
    <unused2157>
    0.37
     théorème
    0.34
     migliorare
    0.32
     jugador
    0.30
     stadiums
    0.29
     nightclubs
    0.29
    رسٹ
    0.28
    เหล่านี้
    0.28
     தோட்டங்கள்
    0.28
     glam
    0.27
    POSITIVE LOGITS
     и
    0.45
     उर्फ
    0.43
    以及
    0.43
     Ltd
    0.43
    and
    0.42
    그리고
    0.41
    そして
    0.39
     sekä
    0.39
     以及
    0.39
     וה
    0.38
    Activations Density 0.093%

    No Known Activations