© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 48225
    Prev
    Next
    INDEX
    Explanations

    greetings like hello or hi

    np_acts-logits-general · gemini-2.5-flash-lite

    AI Prompt, careful with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .?
    0.58
    :,
    0.55
    .&
    0.53
    ",
    0.49
     thêm
    0.48
    .:
    0.47
    .<
    0.47
    hess
    0.46
     没有
    0.46
     遅
    0.45
    POSITIVE LOGITS
    ཟ
    0.42
    த்தர
    0.40
    <0xED>
    0.40
     அப
    0.39
    ინი
    0.39
    ز
    0.39
     takeover
    0.39
    дали
    0.38
    قدم
    0.38
    탭
    0.38
    Activations Density 0.001%

    No Known Activations