© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 10373
    Prev
    Next
    INDEX
    Explanations

    golang code examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_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
     accurate
    0.72
    腸
    0.69
    Note
    0.68
     note
    0.68
     النظر
    0.65
     pang
    0.65
     net
    0.64
     notes
    0.64
     dependent
    0.64
     ha
    0.63
    POSITIVE LOGITS
    ଞ
    0.88
     Añ
    0.85
     метро
    0.83
    𝚞
    0.82
     परिचाल
    0.82
    ोदय
    0.81
    庤
    0.81
    IsEmpty
    0.81
     fluxo
    0.80
    figer
    0.80
    Activations Density 0.003%

    No Known Activations