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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 110843
    Prev
    Next
    INDEX
    Explanations

    various scripts and English concepts

    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
    idade
    0.49
    ión
    0.48
    aping
    0.46
     начало
    0.46
     Terrier
    0.46
    á
    0.46
    ography
    0.45
    ><
    0.44
    acking
    0.44
    ní
    0.44
    POSITIVE LOGITS
    ಾಸ
    0.52
    ಾವ
    0.43
     reconstructed
    0.43
    يال
    0.41
     centralised
    0.41
     sacrificed
    0.41
    랠
    0.39
     اسرائی
    0.39
     Journ
    0.39
    ፔ
    0.39
    Activations Density 0.005%

    No Known Activations