© 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. 208379
    Prev
    Next
    INDEX
    Explanations

    short or clean

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

    know what you meant

    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
     йөк
    0.49
    ποιή
    0.46
    мира
    0.46
    ჟ
    0.45
    Topology
    0.45
    ঝি
    0.45
    қа
    0.44
     своему
    0.44
    лимп
    0.42
    ियाँ
    0.42
    POSITIVE LOGITS
     numeros
    0.49
     usernames
    0.46
     debuts
    0.45
     tattoos
    0.42
     phenotypes
    0.42
     >=
    0.41
    hx
    0.41
     username
    0.41
     diagnoses
    0.40
    uvo
    0.39
    Activations Density 0.000%

    No Known Activations