© 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-3-1B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 4144
    Prev
    Next
    INDEX
    Explanations

    quality control and assurance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_17_width_16k_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
    ствии
    0.96
     flanks
    0.87
    かった
    0.86
     naprawdę
    0.85
    脚
    0.85
    ض
    0.84
     really
    0.84
    からない
    0.83
    really
    0.83
     ease
    0.82
    POSITIVE LOGITS
    流れ
    0.86
     potência
    0.85
    烯
    0.80
     dienst
    0.79
     slike
    0.78
     matter
    0.77
     separación
    0.77
    וח
    0.76
     bieten
    0.75
     vstup
    0.75
    Activations Density 0.069%

    No Known Activations