© 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. 65828
    Prev
    Next
    INDEX
    Explanations

    unexpected post-natal

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

    massive model

    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
    nemonic
    0.56
     ἢ
    0.52
    ]।
    0.49
    peripheral
    0.49
     مک
    0.48
    oreal
    0.48
     होईल
    0.47
     자기
    0.47
     স্পেন
    0.47
     येईल
    0.45
    POSITIVE LOGITS
    d
    0.50
    z
    0.49
     conjuntos
    0.46
    ีย์
    0.46
     etti
    0.45
     compagnie
    0.45
     continuando
    0.44
    c
    0.43
     Have
    0.43
     aplicativos
    0.42
    Activations Density 0.000%

    No Known Activations