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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 55607
    Prev
    Next
    INDEX
    Explanations

    step instructions or warnings

    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
    Де
    0.57
    または
    0.46
    GDP
    0.45
    或
    0.44
    φα
    0.44
     tunnelling
    0.43
    /**
    0.43
    하거나
    0.43
    หรือ
    0.42
     delights
    0.42
    POSITIVE LOGITS
    iyar
    0.44
    ggak
    0.39
    vae
    0.39
    urrection
    0.38
     İyi
    0.38
    Ṭ
    0.38
     đoạn
    0.37
     اچھا
    0.37
    paper
    0.37
    쿄
    0.37
    Activations Density 0.001%

    No Known Activations