© 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. 16-GEMMASCOPE-2-RES-262K
    7. 120365
    Prev
    Next
    INDEX
    Explanations

    override

    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_16_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
    Marne
    0.54
    มะ
    0.53
     दस्ते
    0.53
    login
    0.50
    Alic
    0.49
     Justiça
    0.49
    M
    0.49
    Aqua
    0.48
    éroport
    0.48
     मुं
    0.47
    POSITIVE LOGITS
     spanning
    0.56
     descended
    0.53
    ات
    0.48
    ك
    0.47
    ろう
    0.46
    щу
    0.46
     spanned
    0.46
     dwRes
    0.45
     discouraged
    0.43
     לך
    0.43
    Activations Density 0.001%

    No Known Activations