© 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. 18542
    Prev
    Next
    INDEX
    Explanations

    analysis testing project process

    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
    .
    0.51
     cuidadosamente
    0.48
    地の
    0.44
     immédiatement
    0.43
     فوری
    0.43
     promptly
    0.42
     immediatamente
    0.42
     segera
    0.42
    вому
    0.41
    Iv
    0.41
    POSITIVE LOGITS
    ફેદ
    0.52
    írus
    0.49
     clout
    0.49
     witchcraft
    0.48
     dandruff
    0.48
    郋
    0.47
    }($
    0.46
    ን
    0.46
    カス
    0.45
    רק
    0.45
    Activations Density 0.001%

    No Known Activations