© 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. 137682
    Prev
    Next
    INDEX
    Explanations

    accuracy

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

    value of, differences, send, peak, garlic, limited

    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
    ្សែ
    0.46
    plug
    0.45
    arb
    0.45
    ǎ
    0.45
    veld
    0.44
     plug
    0.42
    plectic
    0.42
    }^{+}\
    0.42
    brack
    0.41
    vedad
    0.40
    POSITIVE LOGITS
     when
    0.47
     by
    0.44
     টাকার
    0.43
     सेब
    0.42
     insolvent
    0.42
    濂
    0.42
    imek
    0.42
    চলে
    0.42
    ının
    0.41
    ৃঙ্খলা
    0.41
    Activations Density 0.002%

    No Known Activations