© 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. 8585
    Prev
    Next
    INDEX
    Explanations

    continuous systems and maintenance

    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
     alerta
    0.52
     yab
    0.49
     communes
    0.49
    words
    0.48
     paralelo
    0.48
     impost
    0.48
    )})
    0.48
     np
    0.47
     disreg
    0.47
     impuestos
    0.47
    POSITIVE LOGITS
     제품
    0.52
     Produkt
    0.47
    连续
    0.44
    动力
    0.43
    得很
    0.43
    眝
    0.43
    தில்
    0.42
     Produk
    0.42
    制品
    0.42
    ibatkan
    0.42
    Activations Density 0.001%

    No Known Activations